No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
On-demand monitoring of construction projects through a game-like hybrid application of BIM and machine learning
Abstract
While unavoidable, inspections, progress monitoring, and comparing as-planned with as-built conditions in construction projects do not readily add tangible intrinsic value to the end-users. In large-scale construction projects, the process of monitoring the implementation of every single part of buildings and reflecting them on the BIM models can become highly labour intensive and error-prone, due to the vast amount of data produced in the form of schedules, reports and photo logs. In order to address the mentioned methodological and technical gap, this paper presents a framework and a proof of concept prototype for on-demand automated simulation of construction projects, integrating some cutting edge IT solutions, namely image processing, machine learning, BIM and Virtual Reality. This study utilised the Unity game engine to integrate data from the original BIM models and the as-built images, which were processed via various computer vision techniques. These methods include object recognition and semantic segmentation for identifying different structural elements through supervised training in order to superimpose the real world images on the as-planned model. The proposed framework leads to an automated update of the 3D virtual environment with states of the construction site. This framework empowers project managers and stockholders with an advanced decision-making tool, highlighting the inconsistencies in an effective manner. This paper contributes to body knowledge by providing a technical exemplar for the integration of ML and image processing approaches with immersive and interactive BIM interfaces , the algorithms and program codes of which can help replicability of these approaches by other scholars.
... Figure 3b shows an example of how a missing element in the real world could be visualized via an AR virtual object. Furthermore, there is the possibility to do this remotely via VR solutions to monitor the current construction progress or to show the current progress to clients [42,53]. For this, there is the need for measurements on-site either by combining different sensors [53] or by using depth images [42]. ...
... Furthermore, there is the possibility to do this remotely via VR solutions to monitor the current construction progress or to show the current progress to clients [42,53]. For this, there is the need for measurements on-site either by combining different sensors [53] or by using depth images [42]. ...
... Construction In the construction phase, 17 approaches use AR [8,10,11,13,19, 20, 23, 24, 26, 33, 35, 38, 43-45, 48, 65], and five approaches use VR [1,5,13,42,53]. Thus, AR is prevalent in this building's lifecycle phase. ...
The Architecture, Engineering, Construction, and Facility Management (AEC/FM) industry deals with the design, construction, and operation of complex buildings. Today, Building Information Modeling (BIM) is used to represent information about a building in a single, non-redundant representation. Here, Augmented Reality (AR) and Virtual Reality (VR) can improve the visualization and interaction with the resulting model by augmenting the real world with information from the BIM model or allowing a user to immerse in a virtual world generated from the BIM model. This can improve the design, construction, and operation of buildings. While an increasing number of studies in HCI, construction, or engineering have shown the potential of using AR and VR technology together with BIM, often research remains focused on individual explorations and key design strategies. In addition to that, a systematic overview and discussion of recent works combining AR/VR with BIM are not yet fully covered. Therefore, this paper systematically reviews recent approaches combining AR/VR with BIM and categorizes the literature by the building’s lifecycle phase while systematically describing relevant use cases. In total, 32 out of 447 papers between 2017 and 2022 were categorized. The categorization shows that most approaches focus on the construction phase and the use case of review and quality assurance. In the design phase, most approaches use VR, while in the construction and operation phases, AR is prevalent.KeywordsDesignConstructionOperationBIMARVR
... Figure 3b shows an example of how a missing element in the real world could be visualized via an AR virtual object. Furthermore, there is the possibility to do this remotely via VR solutions to monitor the current construction progress or to show the current progress to clients [42,53]. For this, there is the need for measurements on-site either by combining different sensors [53] or by using depth images [42]. ...
... Furthermore, there is the possibility to do this remotely via VR solutions to monitor the current construction progress or to show the current progress to clients [42,53]. For this, there is the need for measurements on-site either by combining different sensors [53] or by using depth images [42]. ...
... Construction In the construction phase, 17 approaches use AR [8,10,11,13,19, 20, 23, 24, 26, 33, 35, 38, 43-45, 48, 65], and five approaches use VR [1,5,13,42,53]. Thus, AR is prevalent in this building's lifecycle phase. ...
The Architecture, Engineering, Construction, and Facility Management (AEC/FM) industry deals with the design, construction, and operation of complex buildings. Today, Building Information Modeling (BIM) is used to represent information about a building in a single, non-redundant representation. Here, Augmented Reality (AR) and Virtual Reality (VR) can improve the visualization and interaction with the resulting model by augmenting the real world with information from the BIM model or allowing a user to immerse in a virtual world generated from the BIM model. This can improve the design, construction, and operation of buildings. While an increasing number of studies in HCI, construction, or engineering have shown the potential of using AR and VR technology together with BIM, often research remains focused on individual explorations and key design strategies. In addition to that, a systematic overview and discussion of recent works combining AR/VR with BIM are not yet fully covered. Therefore, this paper systematically reviews recent approaches combining AR/VR with BIM and categorizes the literature by the building's lifecycle phase while systematically describing relevant use cases. In total, 32 out of 447 papers between 2017 and 2022 were categorized. The categorization shows that most approaches focus on the construction phase and the use case of review and quality assurance. In the design phase, most approaches use VR, while in the construction and operation phases, AR is prevalent.
... As indicated in Table 5, a total of 28 articles have been screened in the construction stage, which is the stage with the most harvest across all the stages. A diverse range of research methods have been utilised such as mixed methods [58,95,[117][118][119][120][121][122][123][124][125][126][127][128][129][130][131], modeling [102,[132][133][134][135], and literature review [59,[136][137][138], which suggests that the construction stage is a crucial application stage for ImTs to drive BIM, with a rich variety of studies in terms of both quantity and type. Moreover, the topics of current studies indicate that the majority of studies before year 2019 include AR, followed by MR and DT after year 2019. ...
... Construction management [95,102,[117][118][119][120][132][133][134]: ...
... Since BIM itself lacks the ability to manipulate data to evaluate and predict the real-time status of resources and processes in the construction system, adding a data mining component to the DT system to integrate with BIM and IoT enables informed and objective decision making in situation assessment, prediction, and improvement rather than relying on subjective judgments that may be biased and uncertain [117]. The integration of machine learning and image processing methods with immersive and interactive VR-BIM interfaces also helps with addressing the problems [132]. In addition, using AR to visualise real-time physical environment with each construction activity in the actual environment enables construction managers to make clear and accurate decisions [102]. ...
At present, considering the novelty of Immersive Technologies (ImTs) associated with Digital Twin (DT), Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) in the context of the metaverse and its rapid and ongoing development in Building Information Modeling (BIM), knowledge of specific possibilities and methods for integrating ImTs into building process workflows remains fragmented and scarce. Therefore, this paper aims to explore the research progress and trends of immersive technology-driven BIM applications, providing a helpful reference for understanding the current knowledge system and stimulating future research. To the best of the authors’ knowledge, this is the first attempt to use macro-quantitative bibliometric analysis and micro-qualitative analysis methods to explore the research topic of ImTs-driven BIM. This study obtains 758 related studies in the past decade, year 2013 to 2022, through a series of keywords from the Web of Science Core Collection database and uses VOSviewer software to conduct keywords co-occurrence analysis and overlay visualisation to visualise the relationship between ImTs and BIM, which contains six clusters, namely VR, Internet of Things (IoT), DT, 3D model, design, and AR. The macro-quantitative analysis on ImTs-driven BIM applications throughout all the stages of the building lifecycle reveals the themes, content, and characteristics of the applications across the stages, which tend to be integrated with emerging advanced technology and tools, such as Artificial Intelligence (AI), blockchain, and deep learning.
... The artificial intelligence based on image recognition is making an important contribution in overcoming these gaps: ref. [39] proposed a semi-automatic procedure to generate a systematic, accurate, and convenient digital twinning system pivoting on image surveys and CAD drawings. In [40], the authors presented a framework and a proof-of-concept prototype for on-demand automated replication of construction projects, combining some cutting-edge IT solutions (see Figure 5), specifically, image processing, machine learning, BIM, and virtual reality. Furthermore, a drone-based AI and 3D reconstruction for augmenting the digital twin was presented in [41], demonstrating an Information Fusion framework that goes beyond the capabilities of BIM to enable the integration of heterogeneous data sources. ...
... Figure 5. A photo taken from the construction site (left); photo's depth map (center); output of semantic segmentation for identifying structural building parts (right) (adapted from [40]). ...
... A photo taken from the construction site (left); photo's depth map (center); output of semantic segmentation for identifying structural building parts (right) (adapted from[40]). ...
Artificial Intelligence (AI) is a trending topic in many research areas. In recent years, even building, civil, and structural engineering have also started to face with several new techniques and technologies belonging to this field, such as smart algorithms, big data analysis, deep learning practices, etc. This perspective paper collects the last developments on the use of AI in building engineering, highlighting what the authors consider the most stimulating scientific advancements of recent years, with a specific interest in the acquisition and processing of photographic surveys. Specifically, the authors want to focus both on the applications of artificial intelligence in the field of building engineering, as well as on the evolution of recently widespread technological equipment and tools, emphasizing their mutual integration. Therefore, seven macro-categories have been identified where these issues are addressed: photomodeling; thermal imaging; object recognition; inspections assisted by UAVs; FEM and BIM implementation; structural monitoring; and damage identification. For each category, the main new innovations and the leading research perspectives are highlighted. The article closes with a brief discussion of the primary results and a viewpoint for future lines of research.
... The deterioration of structures, including civil engineering structures and buildings, causes significant damage worldwide every year. Maintenance and repair according to the service lives of structures are needed to reduce such damage, and various structural health monitoring (SHM) systems have been developed, including electronic endoscopes, wireless sensors, and radiofrequency identification devices [1][2][3][4][5]. SHM is a new technology in the fields of civil, mechanical, and aeronautical engineering for detecting structural damage [6]. ...
... The fibers used were 13 mm-long straight steel fibers with a circular cross section and an aspect ratio of 60. The steel fiber used had a density of 7.85 g/cm 3 and a tensile strength of 2700 MPa. Table 2 presents details regarding the prepared specimens with the mix proportion that caused 1.0 mm cracks through the ductile behavior of cement composites [34]. ...
In this study, the deformation of concrete materials was evaluated using a mechanochromic sensor that detects the discoloration reaction caused by deformation. This sensor was attached by applying the Loctite adhesive to both ends in the longitudinal direction. The process of applying tensile stress to the specimens was videotaped, and the deformation and discoloration were examined through image analysis. The mechanochromic sensor was not affected by the finished surface condition, and the discoloration reaction was detected for a concrete material deformation level of up to 0.01 mm. The detected level was caused by the elongation of the sensor, and the discoloration compared with the initial color was identified. In addition, the integration behavior of the mechanochromic sensor under the deterioration of concrete members in cold areas and winter environments, as well as the discoloration reaction of the sensor in a low-temperature environment, was examined. It was found that the discoloration ability of the mechanochromic sensor exposed to a low-temperature environment was restored in 2 h after the end of the freeze–thaw test, and it was judged that the deformation and discoloration levels will be properly measured when the surface temperature of the sensor is restored to a room temperature of approximately 15 °C. This appeared to be due to the room temperature recovery of the dielectric spacer of the sensor and the deformation structure of the resonance condition. The sensor was also attached when diagonal cracks occurred in the concrete beam members to evaluate the strain and discoloration rate according to the deformation and discoloration levels. Accordingly, the cracks and deformation of the concrete materials were monitored using measured values from the discoloration of the mechanochromic sensors, and the possibility of measuring the crack width was reviewed only by real-time monitoring and imaging with the naked eye.
... These new applications are commonly used in various technological combinations to improve construction monitoring and allow models to be compared at the project and actual construction stages. Building information modeling is widely used in construction projects to improve communication between different parties at different stages of project design and implementation [169]. ...
Artificial intelligence covers a variety of methods and disciplines including vision, perception, speech and dialogue, decision making and planning, problem solving, robotics and other applications in which self-learning is possible. The aim of this work was to study the possibilities of using AI algorithms at various stages of construction to ensure the safety of the process. The objects of this research were scientific publications about the use of artificial intelligence in construction and ways to optimize this process. To search for information, Scopus and Web of Science databases were used for the period from the early 1990s (the appearance of the first publication on the topic) until the end of 2022. Generalization was the main method. It has been established that artificial intelligence is a set of technologies and methods used to complement traditional human qualities, such as intelligence as well as analytical and other abilities. The use of 3D modeling for the design of buildings, machine learning for the conceptualization of design in 3D, computer vision, planning for the effective use of construction equipment, artificial intelligence and artificial superintelligence have been studied. It is proven that automatic programming for natural language processing, knowledge-based systems, robots, building maintenance, adaptive strategies, adaptive programming, genetic algorithms and the use of unmanned aircraft systems allow an evaluation of the use of artificial intelligence in construction. The prospects of using AI in construction are shown.
... Later, overcoming the challenges of the occupancy-based techniques, proposed an appearance-based technique that used Machine Learning (ML) assisted construction material classification for operation-level CPM. More recent studies have investigated deep-learning-based object detection from images (Braun et al., 2020) and point clouds (Maalek et al., 2019), advanced Virtual Reality (VR) (Pour Rahimian et al., 2020), Augmented Reality (AR) (Ratajczak et al., 2019), and Mixed Reality (MR) (Kopsida and Brilakis, 2020) techniques for construction progress detection and visualization. ...
Effective progress monitoring is ineviTable for completing the construction of building and infrastructure projects successfully. In this digital transformation era, with the data-centric management and control approach, the effectiveness of monitoring methods is expected to improve dramatically. "Digital Twin," which creates a bidirectional communication flow between a physical entity and its digital counterpart, is found to be a crucial enabling technology for information-aware decision-making systems in manufacturing and other automotive industries. Recognizing the benefits of this technology in production management in construction, researchers have proposed Digital Twin Construction (DTC). DTC leverages building information modeling technology and processes, lean construction practices, on-site digital data collection mechanisms, and Artificial Intelligence (AI) based data analytics for improving construction production planning and control processes. Progress monitoring, a key component in construction production planning and control, can significantly benefit from DTC. However, some knowledge gaps still need to be filled for the practical implementation of DTC for progress monitoring in the built environment domain. This research reviews the existing vision-based progress monitoring methods, studies the evolution of automated vision-based construction progress monitoring research, and highlights the methodological and technological knowledge gaps that must be addressed for DTC-based predictive progress monitoring. Subsequently, it proposes a framework for closed-loop construction control through DTC. Finally, the way forward for fully automated, real-time construction progress monitoring built upon the DTC concept is proposed.
... Traditional two-dimensional design techniques can no longer meet the design requirements and cannot optimize the design of engineering projects (Pan & Zhang, 2023). BIM technology can optimize the construction of difficult structural parts of buildings, such as roofs and curtain walls, and coordinate them using visualization technology (Rahimian et al.,2020). After effectively optimizing these special and complex structural parts, BIM technology can significantly reduce project costs and improve the progress of civil engineering projects, as shown in Figure 1. ...
The aim of this study is to enhance the quality of civil engineering project management and optimize project control in order to ensure adequate construction resources and facilitate seamless project progression. By integrating building information modeling (BIM) technology with deep learning techniques, optimal control was examined at various stages of civil engineering project management. A simulation test was performed on a selected gymnasium engineering project, focusing on cost and resource control aspects. The findings revealed that, as the project advanced, the planned cost exceeded the actual cost by nearly 100,000 yuan in the final stage. The combination of BIM technology and deep learning model prediction substantially reduced the cost and material budgets of the engineering project. Data analysis showed that the average positioning error of the convolutional neural network algorithm for the project model was below 2%.
... This approach is scalable because the time and capital investment for building a virtual construction site are low as compared to implementing the robotic solution on a real construction site. The virtual construction site built in a physics-based game engine can also provide realistic feedback to the robots (Kurien, et al. 2018;Rahimian, et al. 2020) and prevent unsafe incidents in which workers come into contact with the robots. This approach is also flexible because the physical characteristics of the virtual construction sites (e.g., position, dimension, the weight of the target; and the friction effect of the construction product) can be modified, catering to the need of specific construction tasks such as ceiling installation, framing, and paneling. ...
Robots can support onsite workers with repetitive and physically demanding tasks (e.g., bricklaying) to reduce workers’ risk of injuries. Central to the wide application of construction robots is solving the task of motion planning (i.e., moving objects optimally from one location to another under constraints such as joint angle limits). Currently, robots are mostly deployed in the manufacturing phase of a construction project for off-site production of building components. Motions of these robots are pre-programmed and follow strictly designed trajectories and actions. However, the motions of robots on construction sites require considerations of uncertainties, including the onsite movement of material and equipment, as well as changes to workpieces and target locations of the work piece. Therefore, it is essential to enable construction robots to handle these uncertainties while executing construction tasks to extend their applicability onsite. In this study, we proposed an integrated approach combining virtual environments and reinforcement learning (RL) to train robot control algorithms for construction tasks. We first created a virtual construction site using a game engine, which allows for the realistic simulation of robot movements. Next, the physical characteristics of the workpiece (e.g., location) were randomized in the virtual environment to simulate onsite uncertainties. An RL-based robot control algorithm (i.e., Proximal Policy Optimization) was implemented to train the robot for completing a construction task. We tested the robustness and effectiveness of the approach using a testbed construction site for window installation. Results showed that the proposed approach is effective in training the construction robot arm to handle window installation under the uncertainties of window location, with a success rate of 75% for picking up (i.e., grasping) the window and a success rate of 68% for placing the window to its target placement without crashing into other objects onsite. Researchers and practitioners can use the proposed approach to train control algorithms for their specific construction tasks to allow for flexible robot actions considering onsite uncertainties.KeywordsConstruction robotReinforcement learningVirtual environment
... In recent years, the use of UAVs as one of the inexpensive, fast, and accurate automatic digital data collection methods compared to traditional methods, with documentary purposes in the archaeological fields of historical sites, has developed significantly. Also, 3D reconstruction of assets has emerged as a valuable tool for researchers in various fields, including Computer Vision [78] and Machine Learning [79], as well as cultural heritage studies [80]. There are also promising developments in their application for data collection and documentation of historical garden landscapes (see Section 2). ...
Managing, protecting, and the evolutionary development of historical landscapes require robust frameworks and processes for forming datasets and advanced decision support tools. Despite the great potential, using pattern language, machine learning, and regenerative and generative design tools has yet to be adopted in historic landscape research due to the need for suitable training datasets. To address this theoretical and technical gap, this paper describes a three-step workflow, namely photogrammetry, feature extraction and discriminative feature analytics, to help facilitate the use of advanced ML tools for cultural heritage decision support. Sparse-Learning-Modelling (SLM) was used to help with feature extraction from small datasets. The developed tool was successfully tested on the 3D point cloud models of 13 heritage sites, and these could be replicated in other heritage sites with distinctive Cultural DNA worldwide. The findings of this research can extend the discourse of adopting advanced AI/digital tools in heritage landscape design.
... All the literature was published in the last three years, starting from 2018. From Table 2, it could be seen that the research topics are very consistent with the current pain points of the construction industry [75], including monitoring [59,62], safety problems [22,68], schedule [64,66], intelligent equipment [58,63], efficiency [60,70] and waste disposal [61]. For the enabling technologies, plenty of advanced methods and tools are included, just like BIM, Machine Learning, IoT, VR, Blockchain, UAV and Robotics. ...
... Waste management (Bilal et al., 2016b), profitability performance measurement (Bilal et al., 2019), smart road construction, and others (Sharif et al., 2017) typically employ HSPs, while VSPs have been mostly used in construction (Curtis, 2020) and transportation (Shtern et al., 2014). Furthermore, deep learning-based flood detection and damage assessment (Munawar et al., 2021), project delay risk prediction (Gondia et al., 2020), construction site safety (Tixier et al., 2016), construction site monitoring (Rahimian et al., 2020), and neural network models to predict concrete qualities (Maqsoom et al., 2021) are a few instances of AI and ML in construction. ...
The rising volume of heterogeneous data accessible at various phases of the construction process has had a significant impact on the construction industry. The availability of data is especially advantageous in the context of deep renovation, where it may significantly accelerate the decision-making process for building stock retrofit. This chapter covers Big Data and analytics in the context of deep renovation and shows how Machine Learning and Artificial Intelligence have affected the various phases of the deep renovation life cycle. It presents a review of the literature on Big Data and deep renovation and discusses a series of use cases, applications, advantages, and benefits as well as challenges and barriers. Finally, Big Data and deep renovation prospects are discussed, including future potential developments and guidelines.
... The literature has discussed various methods of visualization, including color labels, Augmented Reality (AR) [43,44], 3D model Viewers, Virtual Reality (VR) Environments [18] and Mixed Reality (MR) Environment [24]. Visualization plays a crucial role in enabling the continuous monitoring of construction sites and is considered a predominant method for sites implementing Computer Vision-based Construction Progress Monitoring (CV-CPM) methodology. ...
... It can be envisioned that based on the specific needs, the type of sensors required for data collection and also predictive methods needed for simulation vary significantly (Moyne et al. 2020;Alizadehsalehi and Yitmen 2023). This is amply demonstrated by the multiplicity of frameworks offered for monitoring different aspects of construction assets using the DT concept (Kang et al. 2018;Ignatov and Gade 2019;Rashid et al. 2019;Pour Rahimian et al. 2020;Pan and Zhang 2021). ...
... The execution of VE has been consistent in many construction projects beyond the planning, design, and post-construction phases, including maintenance and operations (Pour et al., 2020). The life cycle of building projects and the continuous increase in risk factors are not conducive to VE development of VE (Wen, 2014). ...
Architectural, Engineering, and Construction industry personnel continuously face challenges in executing projects within budget and schedule. Scheduling and cost control are vital for achieving project success. This study proposed a framework for integrating building information modelling (BIM) and value engineering (VE) methods to enhance value, minimize costs, improve schedules, and support ease of information exchange. The proposed framework provides an option for virtually evaluating material alternatives, design optimization, cost assessment, and improving construction safety. The author used a case study to demonstrate how BIM and VE integration can be harmonized and progressively applied to the design phases through the VE job plan. The findings showed that BIM and VE improved design modification, material evaluations, and detailed data extraction, for example, cost and schedule. The results indicated the significance of using BIM and VE to enhance project functionality, performance, and team coordination throughout the project lifecycle. This study provided the value of integrated BIM and VE, including understanding the project requirements, improving team dynamics, seamless data exchange, and a comprehensive understanding of linking weighted and functional analysis to BIM processes and validated recommended project solutions.
... Further, they raised the issue of not having an efficient information technology (IT)-based resource planning technique for most of the construction projects' failures. According to Pour Rahimian et al. (2020), neither of the preceding approaches for resource planning and allocation included the actual productivity rate while examining the resources. As a result of these incidents, the foundation has been laid for moving into an IT-based resource planning system, of which the history goes back to the 1960s' (Jacobs and Weston, 2007). ...
Purpose
Enterprise resource planning (ERP) systems that are equipped with numerous features and functionalities help to improve the profitability of construction corporations around the world through enhancing the efficiency of the functions related to cost management. Thus, the purpose of this study was to investigate the applicability of ERP systems for cost management of building construction projects in Sri Lanka.
Design/methodology/approach
A qualitative technique was used in this study, which comprised two-round Delphi-based semistructured interviews. Purposive sampling was used to determine the interviewees. Content analysis was used to evaluate the collected data.
Findings
The findings of this study identified the ERP system as a strategic tool for gaining a competitive advantage for an organization while confirming 14 uses of ERP systems and 16 stages of the cost management process. Eighteen issues were finalized at the end of the interview rounds while categorizing the suitable ERP applications at each stage of the cost management process.
Originality/value
Even though there are numerous distinct studies conducted on cost management and ERP systems, there has been a lack of studies conducted on the synergy between these two areas that can be adapted for the building projects in the Sri Lankan context. Therefore, the findings of this study can bring a new paradigm to the Sri Lankan construction sector by influencing the adaption of correct ERP systems at numerous project stages by providing a competitive edge.
... The model was then exported to the Autodesk Naviswork (NWD) file format and saved in the Autodesk Filmbox (FBX) file format, making it suitable for data exchange between different BIM authoring software applications. Finally, the FBX file format was integrated into the Unity game engine with the assigned textures [29]. Fig. 3 (a) and (b) present architectural 3D models of the Department of Civil Engineering Building at Chulalongkorn University. ...
In the past decade, the drawings in construction projects' standard fire evacuation routes are usually guided in two-dimensional (2-D) views to explain hazardous areas and evacuation routes. Common users cannot interpret the drawings quickly, understand their exact position within the building, and select appropriate evacuation routes. Thus, when fires occur, the construction project's fire can cause damages, and the number of dead or injured workers involved can be high. Nowadays, Building Information Modeling (BIM) and Augmented Reality (AR) are used in construction projects to create construction in a three-dimensional (3-D) visualization. This study aims to create a prototype application that combines Building Information Modeling (BIM) and Augmented Reality (AR) to improve the fire evacuation system and provide real-time access to information for evacuating from hazardous locations. A marker-based location system was implemented, using a marker as a spatial index to link the physical location and virtual information. The system was tested for accuracy using the proposed system and the MATALL Laser Distance Meter on the 4th floor of the Department of Civil Engineering Building at Chulalongkorn University. The results showed that the average percentage difference from the current location to the exit measured by the proposed system was lower than that measured by the MATALL Laser Distance meter, with an average percentage difference of less than 2.2%. Therefore, the proposed system effectively provides real-time access to information such as the current location, exit, distance of the shortest route from the current location to the destination, and virtual green line, voice, and arrow direction for evacuation guidance. It is convenient for decision-making and helps users find destinations quickly and efficiently.
... The model was then exported to the Autodesk Naviswork (NWD) file format and saved in the Autodesk Filmbox (FBX) file format, making it suitable for data exchange between different BIM authoring software applications. Finally, the FBX file format was integrated into the Unity game engine with the assigned textures [29]. ...
... This is mainly due to the transformation in the industry regarding procurement combining the change of onsite to offsite construction. As for IoT, extant literature is, for the most part, comprised of conceptual frameworks or is focused on creating point solutions for technical issues [6,20,28]. Given that there is ample opportunity for the integration of IoT and blockchain [2,35], such as automated tracking of project resources, managing supply chain processes, solving the disconnectivity issues in complex projects, managing equipment remotely and supporting the transformation to smart cities. ...
... Radio frequency identification (RFID), global positioning system (GPS), barcode, geographic information system (GIS), and ultra-wideband (UWB) fall under the geospatial techniques category. Whereas videogrammetry, photogrammetry, and laser scanning are part of the imaging techniques category [23]. However, amongst the aforementioned technologies, nine data-acquisition technologies have been classified as close-range in reference to progress monitoring, i.e., AR, swarm nodes, infrared thermography, Kinect sensors, videogrammetry, UWB, photogrammetry, RFID, and laser scanner. ...
Construction industry professionals admire the evolution of digital data-acquisition technologies in monitoring processes due to efficient and efficacious outcomes. However, due to a lack of theoretical insight towards the effective application of these technologies, hesitation has been observed for its adoption, which added a challenge to attaining the Industry 4.0 spirit. This study aims to improve a theoretical, statistically validated model, underlining the operational factors that enhance the performance of the digitized monitoring process. The study has followed the structural equation modeling (SEM) approach on identified 36 factors, which were colligated under four categories for developing the technological-based model. The attained model defines effective technological-based factors for implementing automated monitoring under 'tracking & sensing', 'site video', '3D scanner', and 'site images'. The significance of this model is a provision of a theoretical base to researchers and construction industry professionals in digitized progress monitoring technological operations and technical aspects towards enriched outcomes. Ó 2023 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Ain Shams University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/ by-nc-nd/4.0/).
... Kopsida and Brilakis [8] proposed an indoor progress inspection method based on MR to inspect the progress deviations automatically. AR has the potential for on-site monitoring, project information retrieval, and real-time information sharing [4][5][6]41]. Therefore, some researchers have developed AR applications to realize the in situ presentation of project information and progress inspection data on-site building entities [7,42,43]. ...
Safe and effective construction management requires tools for reducing delays, eliminating reworks, and avoiding accidents. Unfortunately, challenges still exist in current construction practices for enabling real-time interactions among project participants, field discoveries, and massive data. Extended reality (i.e., XR) could help to establish immersive and interactive virtual environments that enable real-time information exchange among humans, cyber processes, and physical environments during construction. However, limited studies have synthesized potentials, challenges, and scenarios of XR for ensuring construction safety and efficiency. This study provides a critical review that synthesizes XR in construction management. First, the authors used the PRISMA method to screen studies related to XR in construction management. Seventy-nine studies were selected and comprehensively analyzed. The authors conducted a bibliometric analysis to comprehend the spatiotemporal distributions of the selected studies. Then, the selected studies were classified into three categories: (1) progress control, (2) quality control, and (3) safety management. The authors also synthesized information for XR applications in various construction management scenarios and summarized the challenges related to XR applications. Finally, this review shed light on future research directions of XR for safe and effective construction management.
... Moreover, this forms the wider understanding of "design-manufacturing-construction" throughout the whole process [25][26][27]. More recently, however, literature has evidenced an increased awareness of pooling together a number of technology-driven solutions, ranging from Building Information Modelling (BIM), Generative Design (GD), Discrete Event Simulations and more recently Digital Twins (DT) to deliver evidencebased solutions for OSC [28]. ...
Several countries have started to more purposefully apply advanced offsite delivery approaches to meet specific housing shortages. The United Kingdom (UK) is no exception. Whilst the concepts and benefits of Modern Methods of Construction are ‘typically’ well understood, it is generally accepted that there is a paucity of knowledge on the actual understanding of optimization per se, ergo, the interrelationships between processes, and the wider understanding of ‘pooling’ [resource management] to promote and maximize synergy - especially to target areas of lag or bottlenecks. In this respect, the research methodological approach adopted in this paper used a single case study to critically evaluate an offsite steel-frame solution for the offsite market to deliver social housing. This approach also evaluated the potential of Generative Design, Discrete Event Simulation, and Digital Twins. Findings of this ongoing research include new opportunities and strategies for these technology-driven solutions, culminating in the development of a new conceptual offsite hub-and-spoke model. These are presented for discussion. This model allows decision-makers to interact with data in order to optimise solutions in line with demand and resource requirements.
... Still, several groups of BC researchers around the world conducted experiments on applying different VR technologies to teach specific BC concepts. Although these experiments mainly focused on managing site conditions (Davidson et al., 2020;Hasanzadeh et al., 2020;Rahimian et al., 2020), some research projects explored how to construct particular building objects using VR innovation. Abdelhameed (2013) developed algorithms in XML code inside the VR Studio program and initiated a simulative function in an effort to assist learners in selecting the structural elements in the building design and structural design processes (p. ...
Construction detail (CD) knowledge is one of the leading learning components in architectural technology (AT) study. The traditional pedagogical method adopts a series of two-dimensional drawings to explain three-dimensional objects. The interactive and immersive features of virtual reality (VR) technology attract attention from the educational sector. While architectural design education has begun exploring integrating VR tools in the classroom, especially in the early design stage, AT is one of the very few subjects that have experimented with VR. This research, undertaken from within a larger, ongoing project, aimed to explore if VR could assist in teaching AT knowledge, especially CD. The project has two phases: phase 1 created several VR lessons that explained specific AT knowledge, using a VR technology currently available for educational purposes; phase 2 adopted a mixed method approach to investigate learners’ experience with the VR lessons created. This paper focuses on the experience in building up a VR learning environment in phase 1. The initial findings after phase 1 showed that the VR technology adopted in this project was not a perfect tool in creating a VR experience in the CD field but could still offer students degrees of virtual reality learning experience.
... It was mainly introduced to differentiate between architectural 3D modeling (BIM) with a lot of information and the established 2D drawings. BIM has been praised by its users because of its ability to detect errors in early stages, making the process more efficient (Pour Rahimian et al., 2020). ...
This study aims to evaluate the utilization of technology known as Digital Twin for fault detection in buildings. The strategy consisted of studying existing applications, difficulties, and possibilities that come with it. The Digital Twin technology is one of the most intriguing newly discovered technologies rapidly evolving; however, some problems still need to be addressed. First, using Digital Twins to detect building faults to prevent future failures and cutting overall costs by improving building maintenance is still ambiguous. Second, how Digital Twin technology may be applied to discover inefficiencies inside the building to optimize energy usage is not well defined. To address these issues, we reviewed 326 documents related to Digital Twin, BIM, and fault detection in civil engineering. Then out of the 326 documents, we reviewed 115 documents related to Digital Twin for fault detection in detail. This study used a qualitative assessment to uncover Digital Twin technology's full fault detection capabilities. Our research concludes that Digital Twins need more development in areas such as scanner hardware and software, detection and prediction algorithms, modeling, and twinning programs before they will be convincing enough for fault detection and prediction. In addition, more building owners, architects, and engineers need substantial financial incentives to invest in condition monitoring before many of the strategies discussed in the reviewed papers will be used in the construction industry. For future investigation, more research needs to be devoted to exploring how machine learning may be integrated with other Digital Twin components to develop new fault detection methods.
Agriculture plays an indispensable role in each country, serving as a major driving force for economic development. It holds the responsibility for producing the majority of the world’s sustenance for the increasing world population, which is expected to reach 9.8 billion by 2050. With the expected population growing substantially, and the lack of precise knowledge from farmers regarding climactic factors, irrigation demand, soil types, yield, market demand, pesticide use, and livestock needs, the farming process is under scrutiny to produce efficient solutions. The recent advances in Machine Learning (ML) have witnessed an extensive number of applications in agriculture to address the issues. ML falls under the category of Artificial Intelligence (AI) where statistical models enable programmable machines to automatically learn from a dataset. This paper surveys various ML algorithms applicable across sub-domains in agriculture, namely, crop management, water management, soil management, and livestock management. This paper discusses the various problems associated with adopting traditional methods such as soil sampling, laboratory analysis, etc. In addition, the ML algorithms proposed by other authors for forecasting or detection are discussed in detail. At last, the future directions for the application of ML in agriculture are illustrated.
The construction industry in Dubai, known for its rapid growth and towering skyscrapers, has faced significant challenges ensuring the safety of its workforce. The purpose of this study was to enhance project management practices through an exploratory factor analysis of safety performance within this sector. This research aimed to identify the underlying factors that contribute to safety outcomes and to provide a data-driven foundation for improving safety measures. Addressing the problem of frequent construction accidents and the high rate of safety incidents, this study hypothesized that a multifaceted approach to safety analysis would reveal complex interdependencies affecting worker safety. The methodology involved a comprehensive review of incident reports and safety records from various construction projects in Dubai over the past five years, coupled with surveys and interviews with industry professionals. The data underwent exploratory factor analysis to ascertain the primary variables impacting safety performance. Findings indicated that key factors affecting safety included worker training, communication efficacy, adherence to safety protocols, and the use of protective equipment. Surprisingly, statistical analysis revealed that projects with high safety investments did not always correlate with lower incident rates, suggesting the importance of qualitative factors over mere financial commitment. The study concludes that enhancing safety performance in Dubai’s construction industry requires a holistic approach that goes beyond financial investment in safety. Recommendations include implementing regular, targeted training programs, improving on-site communication channels, strict enforcement of safety protocols, and fostering a safety-centric organizational culture. In light of these conclusions, the study advocates for policy revisions at the regulatory level and a shift in the industry’s safety paradigm. The recommended strategic changes aim to not only mitigate the risks inherent in the construction industry but also to enhance the overall management of construction projects in the dynamic landscape of Dubai. Keywords. Project Management, Exploratory Factor Analysis, Safety Performance, Construction Industry, Dubai
The Influence of Japanese Kaizen Philosophy on Modern Project Management Practices in Industrial Settings
The primary purpose of this study was to examine how the adoption of Agile Project Management practices can help US-based software companies gain a competitive advantage in the rapidly evolving global marketplace. With ever-increasing customer demands and changing technology landscapes, it was crucial to assess whether agile methodologies could effectively address these challenges. The software industry in the USA faced challenges related to project delays, cost overruns, and difficulties in responding to changing customer requirements. Traditional project management approaches often proved inadequate in such dynamic environments. The study aimed to determine whether Agile Project Management could mitigate these issues and improve competitiveness. The research employed a mixed-methods approach. Quantitative data were collected through surveys distributed to software companies implementing agile practices. Qualitative insights were gathered through in-depth interviews with industry experts. Data analysis involved statistical techniques for quantitative data and thematic analysis for qualitative data. The findings revealed that Agile Project Management significantly improved software development processes. Agile adoption also fostered better collaboration among cross-functional teams. Moreover, Agile practices positively impacted software quality and customer satisfaction, ultimately contributing to a competitive edge. Based on the research findings, it can be concluded that Agile Project Management has a substantial positive impact on the competitiveness of US-based software companies. To enhance competitiveness, it is recommended that US software companies consider the adoption of Agile Project Management practices. Additionally, organizations should invest in training and cultural changes to facilitate a smooth transition to agile methodologies. Continuous improvement and alignment with agile principles are essential for sustained competitiveness. Keywords. Agile Project Management, Software Development, Competitiveness, Customer-Centric, US Software Companies
Building information modeling is one of the trends in the modern construction industry. The use of 4D building information modeling in addition to 3D building information modeling improves project planning and leads to higher quality of the final product with minimal wastage of resources. In addition, 4D building information modeling allows creating visual effects that can be shown to clients before construction begins. The study describes the ways in which 4D building information modeling can be used, as well as some of the notable benefits. The level of awareness of this technology and the level of its use in construction practice are also described. The final part describes the main problems and tasks of this field and possible ways to solve them.
Background:
Although regulatory norms on work safety offer guidelines for organizing and preventing accidents, the construction site is an environment susceptible to deviations, sometimes due to the lack of effective training. To this end, technologies such as virtual reality become possibilities for innovations with great advantages, as they allow simulations, modeling, exploratory environments and games, which allow the user to create a greater connection and interest in the subject in question.
Objective:
This study aimed to present the technological advances applied in safety-oriented training in the construction industry worldwide, emphasizing serious games through a systematic review of the literature.
Methods:
The review was carried out using five scientific databases, with a research protocol to answer questions about the application of gamification to guarantee the safety of workers.
Results:
Fifteen articles were evaluated, with descriptive, observational research and case studies. It was found that the use of technologies in construction safety is not yet a common reality in the sector, as it presents challenges and limitations, such as gameplay and issues related to cost. However, they show great potential as a dynamic solution in the training of civil construction workers, effectively collaborating in accident prevention and work safety.
Conclusion:
Several software programs and applications were found for creating three-dimensional scenes and for providing users with a customized experience according to the needs observed in the virtual interaction; building information modeling tools, which promote realistic project modeling; and equipment to visualize the scenes created. Furthermore, the possibility of combining traditional theoretical teaching with serious games was verified. However, gamification applicability is an alternative that still has limitations, in addition to the lack of flexibility in the rules imposed on the game, hampering users' authenticity in making decisions.
Quality assurance (QA) plays an essential role in the construction project life cycle. During the construction phase, discrepancies between as-built structures and as-designed models can lead to schedule delays and cost overruns. Currently, QA for buildings is primarily conducted by inspectors physically touring the building to visually inspect and manually measure discrepancies between the design model and the finished structure. This manual approach is time-consuming, costly, and error prone. In this study, we proposed a vision-based approach toward automated QA using images collected via virtual cameras in a game engine. Specifically, our approach aimed to address the problem of the lack of large-scale labeled open datasets for training reliable machine learning models for the task of semantic segmentation of building components (i.e., labeling of each pixel to a specific class of building component). The approach leveraged Building Information Modeling (BIM) authoring tools and a game engine to automatically generate images of virtual buildings with pixel-wise labels. Given the labeled images, a convolutional neural network (CNN)-based model can be implemented for accurate segmentation of the images. To validate the approach, we used one building information model as the testbed. In total, 20,700 images (18,000 for training, 2200 for validation and 500 for testing) were generated from the BIM. Performance of the CNN segmentation model was measured by the mean Intersection over Union (MIoU), which achieved 0.89. The result is significant since it rivals the current state-of-the-art from the Architecture Engineering and Construction (AEC) domain. The approach proposed in this study lays a concrete step toward automated QA, where inspectors can leverage the trained CNN model to automatically label images collected onsite during or after construction to avoid labor-intensive manual inspections.KeywordsQuality assuranceBuilding componentsSemantic segmentationSynthetic images
This chapter examines the existing Self-Build Housing Sector in the UK and proposes solutions that utilise BIM, game theory, and immersive technologies to develop an interactive visualisation solution that integrates all of these technologies into one solution. The aim of this solution is to increase the market of TFSBS in the UK. The literature review shows that self-build and group self-build housing projects result in significantly better-quality housing, increased environmental efficiency, and value for money. However, self-building can be daunting and discouraging to purchasers. Additionally, the ZCH standard has been perceived as too complex for construction professionals, and even more so for self-builders. Self-building statistics in Scotland and England have confirmed that UK timber frame kit-home manufacturing companies require growth in BIM maturity levels and would benefit significantly from improved interoperability.KeywordsSelf-build housing sectorBIMZCH standardGame theoryAnd immersive technologies
This study aims to connect project management, network science and machine learning in an accessible overview applied to a real original dataset. Based on an initial literature review of applicable project performance measures and attributes, relevant project data were collected through an online survey. The information was split into three categories, including the basic project measures (five attributes), project stakeholder network measures (seven attributes), and project complexity measures (seven attributes). In total, 70 responses were collected, and five machine learning approaches (i.e. support vector machine, logistic regression, k-nearest neighbour, random forest and extreme gradient boosting) were applied to model the relationships between project attributes, networks and the Iron Triangle of project cost, time and quality. The results confirm the expected trends affecting project performance and provide an example for the discussion of the applicability of integrated machine learning and network analytics approaches to modelling project performance. The article demonstrates in an accessible way a real case of integration of machine learning, network science and project management and suggests avenues for further research and applications in practice.
As one of the most important and advanced technology for carbon-mitigation in the buildings sector, building performance simulation (BPS) has played an increasingly important role with the powerful support of building energy modelling (BEM) technology for energy-efficient designs, operations, and retrofitting of buildings. Owing to its deep integration of multidisciplinary approaches, the researchers, as well as tool developers and practitioners, are facing opportunities and challenges during the application of BEM at multiple scales and stages, e.g., building/system/community levels and planning/design/operation stages. By reviewing recent studies, this paper aims to provide a clear picture of how BEM performs in solving different research questions on varied scales of building phase and spatial resolution, with a focus on the objectives and frameworks, modelling methods and tools, applicability and transferability. To guide future applications of BEM for performance-driven building energy management, we classified the current research trends and future research opportunities into five topics that span through different stages and levels: (1) Simulation for performance-driven design for new building and retrofit design, (2) Model-based operational performance optimization, (3) Integrated simulation using data measurements for digital twin, (4) Building simulation supporting urban energy planning, and (5) Modelling of building-to-grid interaction for demand response. Additionally, future research recommendations are discussed, covering potential applications of BEM through integration with occupancy and behaviour modelling, integration with machine learning, quantification of model uncertainties, and linking to building monitoring systems.
Recent advances in digital photography and unmanned aerial vehicle (UAV) platforms make visual data from construction project sites more accessible to project teams. To semi-automatically or automatically obtain the essential information, evaluate the ongoing activities or operations, and address project-level challenges, researchers have focused on applying various computer vision (CV)-based methods to process and interpret the acquired visual data. This research developed a framework to summarize the vision-based methods that have been applied to construction/asset management operations through a systematic literature review. The reviewed literature was composed of 103 journal papers from 2011 to 2020. All the reviewed journal papers were from the Ei Compendex database with specific search criteria. The developed framework consisted of two parts: use cases and CV domains. Use cases contained five aspects: safety monitoring, productivity improvement, progress monitoring, infrastructure inspection, and robotic application. CV domains contained six aspects: image processing, object classification, object detection, object tracking, pose estimation, and 3D reconstruction. All eleven aspects were integrated from the reviewed papers. For each reviewed paper, the general workflow of applied vision-based approaches was described and categorized into each use case. A trending timeline was developed to analyze the popularity of the identified use cases and CV domains within the reviewed time period. Both the quantity and variety of construction use cases and CV domains have increased. Challenges and limitations of applying CV-based methods in the construction industry were also identified. This paper provides readers with a summary of how CV-based methods have been used in the construction industry and serve as a reference for future research and development.
The architecture, engineering, and construction (AEC) industry stands to benefit tremendously from the integration of lean construction (LC), building information modeling (BIM), and extended reality (XR) technologies at all stages of a project. These technologies enable multidimensional content viewing and collaboration through cloud-based systems and in real-scale environments, resulting in higher levels of efficiency. The aim of this research is to offer an integrative approach that combines project management philosophies, systems, technologies, and tools. The sections containing the results of this study are as follows. (1) A concise review of the benefits of LC, BIM, and XR technologies in the AEC industry, including BIM-based visualization support for LC (Lean-BIM) and BIM visualization in XR (BIM-XR). This section also presents an overview of the most commonly used wearable XRs on the market. (2) The presentation of an LBX process flow diagram and an IDEF0 diagram for the LBX project delivery management system at each stage of AEC projects, including design, construction, and operation. (3) Two possible scenarios for integrated lean, BIM, and XR implementation are suggested, referred to as “in the office” and “online or semi-online LBX meetings”. (4) An analysis of the strengths and weaknesses of the LBX management system, practical implications, and open challenges of applying LBX to project management tasks. Overall, this study presents an enormous opportunity to increase the quality of construction project planning, understanding, and performance, and provides a roadmap for future efforts to implement the integration of LC, BIM, and XR technologies in the AEC industry.
The Architecture and Construction industry is currently experiencing a transformation from the traditional approach to a more robust and efficient approach through the adoption of information technology. But still in developing country like India, it is still at an early stage and yet to realize its full potential. The aim of this paper is to first find out the various challenges in the Office Fit-Out Construction which is a type of Fast track construction approach and then link it with the various digital technologies that could be used to mitigate these challenges and enhance the smooth management both for the client and the executing firm. From the literature study and the expert interviews various challenges has been identified and its validation & frequency of occurrence is checked by undergoing various case studies. Various reasons for these challenges has been identified and listed through fish bone diagram. And checked Further how the technology and various digital tools present in the market could help in minimizing these causes. The results then analyzed to check of its implication at site and suggesting appropriate measures for the better management of Office Fit-Out Projects through Digitalization.
The construction industry is expanding since it significantly contributes to the economy. At the same time, the skilled labor shortage in the United States makes it challenging to manage the high demands of the construction process. According to the Associated General Contractors of America (AGC) construction industry creates nearly $1.4 trillion worth of structures each year; therefore, to accompany the enormous budget, the shortage of skilled labor, and the limited construction durations,
it is proposed to provide an automated method in the construction process that mainly utilizes Mask R-CNN models in detecting the activity of masonry walls construction.
Quantitative analysis and conclusive research methodology were performed to train, test, and evaluate the developed computer vision models (i.e., YOLOv4, YOLOv4- Tiny, and Mask R-CNN) using Google Colab Pro. The models were trained and tested on forty masonry walls with more than two thousand bricks annotated that differ in pattern and location, in addition to physical and environmental conditions. The bricks’
masks were combined in a 3D matrix and converted to the surface area representing the masonry wall progress ratio. The monitoring progress percentage is translated to the Building Information Modeling (BIM) through Dynamo. Experimented data were used to validate the performance of the adopted Mask R-CNN model in different
scenarios using JMP Pro 16. A structural equation model (SEM) was proposed to show the causal relationship between the variables.
The developed computer vision models had a maximum accuracy of 84%, recall of 95%, mean average precision of 96%, intersection over union of 72%, and errors of 11% in detecting bricks in masonry walls. The SEM had a root mean square error of approximation of 0.1134 and a comparative fix index of 0.9674. Three hypotheses were developed and tested; the results showed that the only significant relationship on the estimated area through the Mask R-CNN model was the actual area of the wall. An
IDEF0 was proposed to demonstrate the concept of construction progress monitoring using up-to-date inspection technologies. The IDEF0 process was developed to show the flow of stages during construction progress monitoring.
The research integrates Dynamo with the Mask R-CNN model to detect and reflect BIM 3D models' progress by summating generated masks’ matrices. It shows the interaction of BIM and drones in masonry wall progress monitoring, data collection, and the possibility of detecting brick elements using their location when following the IDEF0 process.
Purpose
Rebar is the prime component of reinforced concrete structures, and rebar monitoring is a time-consuming and technical job. With the emergence of the fourth industrial revolution, the construction industry practices have evolved toward digitalization. Still, hesitation remains among stakeholders toward the adoption of advanced technologies and one of the significant reasons is the unavailability of knowledge frameworks and implementation guidelines. This study aims to investigate technical factors impacting automated monitoring of rebar for the understanding, confidence gain and effective implementation by construction industry stakeholders.
Design/methodology/approach
A structured study pipeline has been adopted, which includes a systematic literature collection, semistructured interviews, pilot survey, questionnaire survey and statistical analyses via merging two techniques, i.e. structural equation modeling and relative importance index.
Findings
The achieved model highlights “digital images” and “scanning” as two main categories being adopted for automated rebar monitoring. Moreover, “external influence”, “data-capturing”, “image quality”, and “environment” have been identified as the main factors under “digital images”. On the other hand, “object distance”, “rebar shape”, “occlusion” and “rebar spacing” have been highlighted as the main contributing factors under “scanning”.
Originality/value
The study provides a base guideline for the construction industry stakeholders to gain confidence in automated monitoring of rebar via vision-based technologies and effective implementation of the progress-monitoring processes. This study, via structured data collection, performed qualitative and quantitative analyses to investigate technical factors for effective rebar monitoring via vision-based technologies in the form of a mathematical model.
Industry executives in the Architecture, Engineering, and Construction (AEC) business have deliberately escalated the need for precise, unambiguous, and intuitive knowledge. Industry 4.0 is of paramount importance towards the formation of a virtual logistics system in AEC that facilitates automation in manufacturing operations and acts as a link between distinct stakeholders and construction initiatives. Immersive Virtual and Augmented Reality (VAR) technologies are rolling out in many entertainment and scientific areas as consumer-based Head-Mounted Displays (HMDs) become more ubiquitous. Furthermore, VAR innovations have great practical utility in the AEC industry due to improvements in Building Information Modeling (BIM). Although the AEC business has been reluctant to adopt VAR innovations in comparison to certain other sectors, mainly due to a paucity of reliable research contrasting the rise in benefits versus the unit price of deployment. This study aims to explore the dynamics of the industry in VAR technology adoption and addresses AEC strategic initiatives. Moreover, this paper discusses the VAR use cases in the AEC industry, along with its challenges and immersive VAR technology for BIM.
There is a lack of research on the use of Artificial Intelligence (AI) within the construction sector in the UK. Therefore, this research seeks to explore AI uses and its benefits on the UK construction industry. Given the new and unexplored nature of the research problem, a qualitative case study research methodology was adopted. Construction projects, which have adopted some of the AI forms all around the UK, are investigated extracting the use of the technology and how processes within the construction industry can benefit from the adoption of AI. Developing an AI system can benefit the construction industry in terms of the planning process, organizations have implemented AI systems to accomplish tasks such as tunnel inspections, safety hazard identifying, and risk management. These implementations have proved to be successful and efficient in improving production within the organizations. This paper highlights the key uses and benefits of AI-based systems within the construction industry. The business model was developed based on current work practices with AI and without AI. It is concluded that the industry as a whole should enhance coordination and cooperation across the value chain and agree on common goals and standards for the adoption of AI.
Purpose
Dynamic planning and scheduling forms a widely adopted smart strategy for solving real-world problems in diverse business systems. This paper uses deductive content analysis to explore secondary data from previous studies in dynamic planning and scheduling to draw conclusions on its current status, forward action and research needs in construction management.
Design/methodology/approach
The authors searched academic databases using planning and scheduling keywords without a periodic setting. This research collected secondary data from the database to draw an objective comparison of categories and conclusions about how the data relates to planning and scheduling to avoid the subjective responses from questionnaires and interviews. Then, applying inclusion and exclusion criteria, we selected one hundred and four articles. Finally, the study used a seven-step deductive content analysis to develop the categorisation matrix and sub-themes for describing the dynamic planning and scheduling categories. The authors used deductive analysis because of the secondary data and categories comparison. Using the event types represented in a quadrant mapping, authors delve into where, when, application and benefits of the classes.
Findings
The content analysis showed that all the accounts and descriptions of dynamic planning and scheduling are identifiable in an extensive research database. The content analysis reveals the need for multi-hybrid (4D BIM-Agent based-discrete event-discrete rate-system dynamics) simulation modelling and optimisation method for proffering solutions to scheduling and planning problems, its current status, tools and obstacles.
Originality/value
This research reveals the deductive content analysis talent in construction research. It also draws direction, focuses and raises a question on dynamic planning and scheduling research concerning the five-integrated model, an opportunity for their integration, models combined attributes and insight into its solution viability in construction.
Thorough and organized documentation is crucial for conservation of historic structures. While photogrammetry, laser scanning and building information modeling (BIM) have enhanced 3D documentation in conservation, it is imperative that the method of documentation matches the requirements of the project. Present methods are efficient for certain types of projects. However, for projects that need to depict 3D conservation challenges, but do not have the budget or time for a 3D model, a middle ground does not exist. Extended reality technologies can simulate historic buildings and sites in a multidimensional digital model and offer different aspects of it. Virtual reality is a new technology that allows the user to interact with a computer simulation environment. A virtual tour is a simulation of a real place created using media files such as photos, 360-degree
panoramic images, video, text, narration, music, and more. In this research, a suitable solution has been presented using virtual tour environments and information modeling, and this solution has been studied on a case study of Kermanshah arch. The virtual tour environment created includes an image gallery, database, text, music, and a 3D photogrammetric model. In this research, both photogrammetric and virtual tour methods have been used to construct a documentary model of the vault and the model has been shared directly on the web.
There have been numerous simulation tools utilised for calculating building energy loads for efficient design and retrofitting. However, these tools entail a great deal of computational cost and prior knowledge to work with. Machine Learning (ML) techniques can contribute to bridging this gap by taking advantage of existing historical data for forecasting new samples and lead to informed decisions. This study investigated the accuracy of most popular ML models in the prediction of buildings heating and cooling loads carrying out specific tuning for each ML model and using two simulated building energy data generated in EnergyPlus and Ecotect and compared the results. The study used a grid-search coupled with cross-validation method to examine the combinations of model parameters. Furthermore, sensitivity analysis techniques were used to evaluate the importance of input variables on the performance of ML models. The accuracy and time complexity of models in predicting heating and cooling loads are demonstrated. Comparing the accuracy of the tuned models with the original research works reveals the significant role of model optimisation. The outcomes of the sensitivity analysis are demonstrated as relative importance which resulted in the identification of unimportant variables and faster model fitting.
As a result of progressive use of BIM in the AEC sector, the amount of diverse project information is increasing rapidly, thus necessitating interoperability of tools, compatibility of data, effective collaboration and sophisticated data management. Media-rich VR and AR environments have been proven to help users better understand design solutions, however, they have not been quite advanced in supporting interoperability and collaboration. Relying on capabilities of openBIM and IFC schema, this study posits that this shortcoming of VR and AR environment could be addressed by use of BIM server concept allowing for concurrent multiuser and low-latency communication between applications. Successful implementation of this concept can ultimately mitigate the need for advanced technical skills for participation in design processes and facilitate the generation of more useful design solutions by early involvement of stakeholders and end-users in decision making. This paper exemplifies a method for integration of BIM data into immersive VR and AR environments, in order to streamline the design process and provide a pared-down agnostic openBIM system with low latency and synchronised concurrent user accessibility that gives the "right information to the right people at the right time". These concepts have been further demonstrated through development of a prototype for openBIM-Tango integrated virtual showroom for offsite manufactured production of self-build housing. The prototype directly includes BIM models and data from IFC format and interactively presents them to users on both VR immersive and AR environments, including Google Tango enabled devices. This paper contributes by offering innovative and practical solutions for integration of openBIM and VR/AR interfaces, which can address interoperability issues of the AEC industry.
Abstract Ever growing population and progressive municipal business demands for constructing new buildings are known as the foremost contributor to greenhouse gasses. Therefore, improvement of energy efficiency of the building sector has become an essential target to reduce the amount of gas emission as well as fossil fuel consumption. One most effective approach to reducing CO2 emission and energy consumption with regards to new buildings is to consider energy efficiency at a very early design stage. On the other hand,efficient energy management and smart refurbishments can enhance energy performance of the existing stock. All these solutions entail accurate energy prediction for optimal decision making. In recent years, artificial intelligence (AI) in general and machine learning (ML) techniques in specific terms have been proposed for forecasting of building energy consumption and performance. This paper provides a substantial review on the four main ML approaches including artificial neural network, support vector machine, Gaussian-based regressions and clustering, which have commonly been applied in forecasting and improving building energy performance.
Defects and errors in new or recently completed construction work continually pervade the industry. Whilst inspection and monitoring processes are established vehicles for their 'control', the procedures involved are often process driven, time consuming, and resource intensive. Paradoxically therefore, they can impinge upon the broader aspects of project time, cost and quality outcomes. Acknowledging this means appreciating concatenation effects such as the potential for litigation, impact on other processes and influence on stakeholders' perceptions—that in turn, can impede progress and stifle opportunities for process optimisation or innovation. That is, opportunities relating to for example, logistics, carbon reduction, health and safety, efficiency, asset underutilisation and efficient labour distribution. This study evaluates these kinds of challenge from a time, cost and quality perspective, with a focus on identifying opportunities for process innovation and optimisation. It reviews—within the construction domain—state of the art technologies that support optimal use of artificial intelligence, cybernetics and complex adaptive systems. From this, conceptual framework is proposed for development of real-time intelligent observational platform supported by advanced intelligent agents, presented for discussion. This platform actively, autonomously and seamlessly manages intelligent agents (Virtual Reality cameras, Radio-Frequency Identification RFID scanners, remote sensors, etc.) in order to identify, report and document 'high risk' defects. Findings underpin a new ontological model that supports ongoing development of a dynamic, self-organised sensor (agent) network, for capturing and reporting real-time construction site data. The model is a 'stepping stone' for advancement of independent intelligent agents, embracing sensory and computational support, able to perform complicated (previously manual) tasks that provide optimal, dynamic, and autonomous management functions.
On-site construction inspection for progress monitoring is a manual, time consuming and labour intensive pro-cess consumed by exhaustive manual extraction of data from drawings and databases. Efforts have been made to facilitate the inspection process by using emerging technologies such as Augmented Reality (AR). AR based systems can simplify and reduce the time of inspection by providing the inspector with instantane-ous access to the information stored in the Building Information Modelling (BIM). However, precise align-ment between the BIM model and the real world scene is still a challenge. For estimating the position and ori-entation of the user, methods have been proposed that either use markers or confine the user to a specific loca-tion, or use Global Positioning System (GPS) which cannot operate efficiently in an indoor environment. This paper presents an evaluation of different methods that could potentially be used for a marker-less BIM regis-tration in AR. We implemented and tested line, edge, and contour detection algorithms using images, data from LSD and ORB Simultaneous Localisation and Mapping (SLAM) methods and 3D and positioning data from Kinect sensor and Google Project Tango. The results indicate that sparse 3D data is the input dataset that leads to the most robust results when combined with XYZ method.
A growing awareness in the construction industry has emerged to pay a sharp attention to ICT as a catalyst that would mitigate the deficiencies characterized by this industry. In comparison with other cited review articles, this paper is aimed to 1) compile the research published on “ICT Technologies” in correspondence to “Construction Tasks” in the construction industry over the past two decades (1996- 2016), 2) demonstrate the trends and patterns in the use of different types of ICT Technologies 3) discuss the correspondence of the identified ICT Technologies to the identified Construction Tasks and 4) exhibit the construction needs of ICT. By the employment of a five phases profiling methodology, a set of 68 out of 202 articles and papers indexed by Elsevier’s Scopus database was considered relevant for the current review paper. This research is targeting the beginning researchers and practitioners in the field of ICT in construction
Construction safety management has been a popular issue in research and practice in recent years due to the high accident and death rates in the construction industry. The complexity and variability of construction sites makes safety management more difficult to implement than in other industries. As a promising technology, visualization has been extensively explored to aid construction safety management. However, a comprehensive critical review of the visualization technology in construction safety management is absent in the literature.
In this paper we address the problem of semantic labeling of indoor scenes on RGB-D data. With the availability of RGB-D cameras, it is expected that additional depth measurement will improve the accuracy. Here we investigate a solution how to incorporate complementary depth information into a semantic segmentation framework by making use of convolutional neural networks (CNNs). Recently encoder-decoder type fully convolutional CNN architectures have achieved a great success in the field of semantic segmentation. Motivated by this observation we propose an encoder-decoder type network, where the encoder part is composed of two branches of networks that simultaneously extract features from RGB and depth images and fuse depth features into the RGB feature maps as the network goes deeper. Comprehensive experimental evaluations demonstrate that the proposed fusion-based architecture achieves competitive results with the state-of-the-art methods on the challenging SUN RGB-D benchmark obtaining 76.27% global accuracy , 48.30% average class accuracy and 37.29% average intersection-over-union score.
This work presents a Multi-View Stereo system for robust and efficient dense modeling from unstructured image collections. Our core contributions are the joint estimation of depth and normal information , pixelwise view selection using photometric and geometric priors , and a multi-view geometric consistency term for the simultaneous refinement and image-based depth and normal fusion. Experiments on benchmarks and large-scale Internet photo collections demonstrate state-of-the-art performance in terms of accuracy, completeness, and efficiency.
Incremental Structure-from-Motion is a prevalent strategy for 3D reconstruction from unordered image collections. While incremental reconstruction systems have tremendously advanced in all regards, robustness, accuracy , completeness, and scalability remain the key problems towards building a truly general-purpose pipeline. We propose a new SfM technique that improves upon the state of the art to make a further step towards this ultimate goal. The full reconstruction pipeline is released to the public as an open-source implementation.
Over the past few years, the application of camera-equipped Unmanned Aerial Vehicles (UAVs) for visually monitoring construction and operation of buildings, bridges, and other types of civil infrastructure systems has exponentially grown. These platforms can frequently survey construction sites, monitor work-in-progress, create documents for safety, and inspect existing structures, particularly for hard-to-reach areas. The purpose of this paper is to provide a concise review of the most recent methods that streamline collection, analysis, visualization, and communication of the visual data captured from these platforms, with and without using Building Information Models (BIM) as a priori information. Specifically, the most relevant works from Civil Engineering, Computer Vision, and Robotics communities are presented and compared in terms of their potential to lead to automatic construction monitoring and civil infrastructure condition assessment.
This research discusses the implementation of Radio Frequency Identification (RFID) and Virtual Reality (VR) simulations in construction processes and projects. The purposes are to improve the control and monitor of construction projects and to find the optimized solutions for construction processes. The authors have implemented a Building Information Model (BIM) and used it in a VR world. The details of the BIM model are the basis for the optimization analysis in construction. Using VR technology in the analysis helps the architect, engineer, and contractor (A/E/C) team to understand construction projects and plans. The team can gain experience by developing and critiquing construction sequences in a full-scale virtual environment. The team can also gain interactive operation, simulation, and optimization experiences. VR simulations in construction should not only focus on the pre-construction stage, but also record the site changes and update the system in real time. The real-time VR simulation in this study can be used throughout the entire construction process. In particular, the technology will help in the optimization of steel installation sequencing during construction. The real-time VR simulation is done via the use of RFID and its related database. In this study, the authors are experimenting with the use of a data hub for staging and cleansing the data before feeding it into the BIM database. This BIM/RFID enriched VR environment improves the straight forward representations which VR simulation can provide, automates construction data collection by acquiring RFID in real time, and accomplishes data integration through the use of BIM. The A/E/C team can use the system to explore different construction sequences, temporarily re-arrange facility or equipment locations, coordinate trades, identify safety issues, and improve constructability.
This paper presents a new appearance-based material classification method for monitoring construction progress deviations at the operational-level. The method leverages 4D Building Information Models (BIM) and 3D point cloud models generated from site photologs using Structure-from-Motion techniques. To initialize, a user manually assigns correspondences between the point cloud model and BIM, which automatically brings in the photos and the 4D BIM into alignment from all camera viewpoints. Through reasoning about occlusion, each BIM element is back-projected on all images that see that element. From these back-projections, several 2D patches are sampled per element and are classified into different material types. To perform material classification, the expected material type information is derived from BIM. Then the image patches are convolved with texture and color filters and their concatenated vector-quantized responses are compared with multiple discriminative material classification models that are relevant to the expected progress of that element. For each element, a quantized histogram of the observed material types is formed and the material type with the highest appearance frequency infers the appearance and thus the state of progress. To validate, four new datasets of incomplete and noisy point cloud models are introduced which are assembled from real-world construction site images and BIMs. An extended version of the Construction Material Library (CML) is also introduced for training/testing the material classifiers. The material classification shows an average accuracy of 92.4% for CML image patches of 100 × 100 pixels. The experiments on those four datasets show an accuracy of 95.9%, demonstrating the potential of appearance-based recognition method for inferring the actual state of construction progress for BIM elements.
On-site progress monitoring is essential for keeping track of the ongoing work on construction sites. Currently, this task is a manual, time-consuming activity. The research presented here, describes a concept for an automated comparison of the actual state of construction with the planned state for the early detection of deviations in the construction process. The actual state of the construction site is detected by photogrammetric surveys. From these recordings, dense point clouds are generated by the fusion of disparity maps created with semi-global-matching (SGM). These are matched against the target state provided by a 4D Building Information Model (BIM). For matching the point cloud and the BIM, the distances between individual points of the cloud and a componentÕs surface are aggregated using a regular cell grid. For each cell, the degree of coverage is determined. Based on this, a confidence value is computed which serves as basis for the existence decision concerning the respective component. Additionally, process- and dependency-relations are included to further enhance the detection process. Experimental results from a real-world case study are presented and discussed.
Building Information Models (BIMs) are becoming the official standard in the construction industry for
encoding, reusing, and exchanging information about structural assets. Automatically generating such
representations for existing assets stirs up the interest of various industrial, academic, and governmental
parties, as it is expected to have a high economic impact. The purpose of this paper is to provide a general
overview of the as-built modelling process, with focus on the geometric modelling side. Relevant works
from the Computer Vision, Geometry Processing, and Civil Engineering communities are presented and
compared in terms of their potential to lead to automatic as-built modelling.
Construction phase still presents many difficulties and contingencies related to the project documents information management between the actors involved. Different studies investigated methods and models to optimize the operational management of the construction phase. Concerning workers’ health and safety protection most of them focused on the development of on-site and in real-time control systems. Therefore, the authors identified the exigency of a prevention information system based on workers’ involvement. To reach the aim three objectives have been identified: (1) the check of workers’ training, (2) the definition of works operational procedures and (3) the schematization of the assembly/disassembly/use of site equipment and temporary structures. The developed system is characterized by a synergic application of BIM model and QR-code and it has been applied on a case study. At the same time a questionnaire has been developed and proposed to different subjects of the construction sector in order to evaluate the potential use of BIM model and QR-code. The field test has allowed to demonstrate the practical use of the tool, enhancing communication between the Client technical structure, the General contractor and sub-contractors, improving workers’ integration and participation and allowing a better availability of on-site health and safety information and documents.
The problem of housing delivery is of great concern in many countries of the world. This problem is more predominant in developing countries and Nigeria is not an exception. In Nigeria, this challenge has been magnified as a result of myriad of issues, e.g. high population growth rate, shortage of necessary skills, disintegrated supply chain etc. Seminal literature has proven that offsite manufacturing (OSM) can help improve housing delivery efforts both in terms of quantity and quality. The purpose of the research was to investigate the current housing delivery problems in Nigeria and evaluate the feasibility of adopting OSM. To achieve this, the study conducted substantial literature review to explore the benefits of OSM, identify the problems of housing delivery in Nigeria and explore different dimensions and the issues that can be associated with using OSM in Nigeria. The results revealed that there are a good number of benefits promised by OSM; notable among these benefits are: less wastage on site, faster construction time, quality improvement and reduction in wet trades. Moreover, some of the problems of housing delivery in Nigeria identified included: skills shortage, reliance on conventional construction techniques, slow pace of construction, and low quality of housing. The study also showed that adaptation of OSM has been quite useful in other countries facing the similar issues of housing shortage, e.g. Malaysia. As such, it is argued that OSM can improve skills shortages, improve the speed of construction, improve the overall quality of housing and help eliminate wet trades. For the problems of housing delivery to be tackled in Nigeria, it is important to undertake additional research to identify the benefits, barriers and context-specific ways of adopting OSM in Nigeria.
As-built spatial data are useful in many construction-related applications, such as quality control and progress monitoring. These data can be collected using a number of imaging and time-of-flight-based (e. g., laser scanning) sensor methods. Each application will demand a particular level of data accuracy and quality, yet little information is available to help engineers choose the most cost-effective approach. This paper presents an analytical and quantitative comparison of photogrammetric, videogrammetric, and time-of-flight-based methods. This comparison is done with respect to accuracy, quality, time efficiency, and cost. To this end, representative image-based three-dimensional reconstruction software and commercially available hardware (two cameras and a time-of-flight-based laser scanner) are evaluated. Spatial data of typical infrastructure (two bridges and a building) are collected under different settings. The experimental parameters include camera type, resolution, and shooting distance for the imaging sensors. By comparing these data with the ground truth collected by a total station, it is revealed that video/photogrammetry can produce results of moderate accuracy and quality but at a much lower cost as compared to laser scanning. The obtained information is useful to help engineers make cost-effective decisions and help researchers better understand the performance impact of these settings for the sensor technologies. DOI: 10.1061/(ASCE)CO.1943-7862.0000565. (C) 2013 American Society of Civil Engineers.
In this paper we study the problem of object detection for RGB-D images using
semantically rich image and depth features. We propose a new geocentric
embedding for depth images that encodes height above ground and angle with
gravity for each pixel in addition to the horizontal disparity. We demonstrate
that this geocentric embedding works better than using raw depth images for
learning feature representations with convolutional neural networks. Our final
object detection system achieves an average precision of 37.3%, which is a 56%
relative improvement over existing methods. We then focus on the task of
instance segmentation where we label pixels belonging to object instances found
by our detector. For this task, we propose a decision forest approach that
classifies pixels in the detection window as foreground or background using a
family of unary and binary tests that query shape and geocentric pose features.
Finally, we use the output from our object detectors in an existing superpixel
classification framework for semantic scene segmentation and achieve a 24%
relative improvement over current state-of-the-art for the object categories
that we study. We believe advances such as those represented in this paper will
facilitate the use of perception in fields like robotics.
Background
Global competition and the transdisciplinary nature of evolving Architecture-Engineering-Construction (AEC) activities makes it progressively important to educate new AEC professionals with appropriate skill sets. These skills include the ability and capability of not only developing routine projects, but also delivering novel design solutions and construction processes (some of which may be unknown), to feasible, surprising, or potentially patentable solutions. For example, despite recent innovations in immersive visualisation technologies and tele-presence decision-support toolkits, the AEC sector as a whole has not yet fully understood these technologies, nor embraced them as an enabler.
Methods
Given this, this paper proposes a new approach for delivering education and training to address this shortcoming. This approach focuses on doing traditional (routine) work with creative thinking in order to address these challenges. This rationale is based on the principles of Successful Education as a new paradigm for engineering education, which is inspired by the Theory of Successful Intelligence, by the Medici Effect and Leonardo da Vinci’s Seven Principles. The paper presents the educating AEC professionals is presented the AEC sector. The Theory of Successful Intelligence and its three forms of intelligence (Practical, Analytical, and Creative), are supported by lessons learned from the Renaissance, including the Medici Effect and da Vinci’s Seven Principles.
Results
Based on these theoretical pillars, a new approach to educating AEC professionals is presented with a proof-of-concept prototype that uses a game-like virtual reality (VR) visualisation interface supported by Mind Mapping is introduced as an exemplar.
Conclusion
The developed interface in this study applies Game Theory to non-collocated design teams in accordance with Social Sciences Theory (social rules) and Behavioural Science Theory (decision making). It contributes by supporting new insights into AEC actor involvement, pedagogy, organisational behaviour, and the social constructs that support decision making.
We describe two new approaches to human pose estimation. Both can quickly and accurately predict the 3D positions of body joints from a single depth image without using any temporal information. The key to both approaches is the use of a large, realistic, and highly varied synthetic set of training images. This allows us to learn models that are largely invariant to factors such as pose, body shape, field-of-view cropping, and clothing. Our first approach employs an intermediate body parts representation, designed so that an accurate per-pixel classification of the parts will localize the joints of the body. The second approach instead directly regresses the positions of body joints. By using simple depth pixel comparison features and parallelizable decision forests, both approaches can run super-real time on consumer hardware. Our evaluation investigates many aspects of our methods, and compares the approaches to each other and to the state of the art. Results on silhouettes suggest broader applicability to other imaging modalities.
In this paper, we propose a framework for interactive image segmentation. The goal of interactive image segmentation is to classify the image pixels into foreground and background classes, when some foreground and background markers are given. The proposed method minimizes a min–max Bayesian criterion that has been successfully used on image segmentation problem and it consists of several steps in order to take into account visual information as well as the given markers, without any requirement of training. First, we partition the image into contiguous and perceptually similar regions (superpixels). Then, we construct a weighted graph that represents the superpixels and the connections between them. An efficient algorithm for graph clustering based on synthetic coordinates is used yielding an initial map of classified pixels. This method reduces the problem of graph clustering to the simpler problem of point clustering, instead of solving the problem on the graph data structure, as most of the known algorithms from literature do. Finally, having available the data modeling and the initial map of classified pixels, we use a Markov Random Field (MRF) model or a flooding algorithm to get the image segmentation by minimizing a min–max Bayesian criterion. Experimental results and comparisons with other methods from the literature are presented on LHI, Gulshan and Zhao datasets, demonstrating the high performance and accuracy of the proposed scheme.
A number of methods are commonly used today to collect infrastructure's spatial data (time-of-flight, visual triangulation, etc.). However, current practice lacks a solution that is accurate, automatic, and cost-efficient at the same time. This paper presents a videogrammetric framework for acquiring spatial data of infrastructure which holds the promise to address this limitation. It uses a calibrated set of low-cost high resolution video cameras that is progressively traversed around the scene and aims to produce a dense D point cloud which is updated in each frame. It allows for progressive reconstruction as opposed to point-and-shoot followed by point cloud stitching. The feasibility of the framework is studied in this paper. Required steps through this process are presented and the unique challenges of each step are identified. Results specific to each step are also presented.
Concrete pouring represents a major critical path activity that is often affected by design limitations, structural considerations and on-site operational constraints. As such, meticulous planning is required to ensure that both the aesthetic and structural integrity of joints between cast in-situ components is achieved. Failure to adequately plan concrete pouring could lead to structural defects, construction rework or structural instability, all having major financial implications. Given the inherent complexity of large-scale construction projects, the 'manual planning' of concrete pouring is a challenging task and prone to human errors. Against this backdrop, this study developed 4D Building Information Management (BIM) approach to facilitate automated concrete joint positioning solution (as a proof of concept) for design professionals and contractors. The study first developed structural model in Revit, then extracted spatial information regarding all construction joints and linked them to dynamic Microsoft (MS) Excel and Matlab spreadsheets using integration facilitated by Dynamo software. Midspan points of each beam as well as floor perimeter information were gathered via codes developed in MS Excel macros. Based on the Excel outputs, Matlab programming was used to determine best concreating starting points and directions, and daily allowed concrete volume, considering limitations due to cold joints. These information were then pushed back to Revit via Dynamo in order to develop daily concrete scheduling. The developed automated programme framework offers a cost-effective and accurate methodology to address the limitations and inefficiencies of traditional methods of designing construction joints and planning pours. This framework extends the body of knowledge by introducing innovative solutions to integrate structural design considerations, constructional procedures and operational aspects for mitigating human error, and providing a novel, yet technically sound, basis for further application of BIM in structural engineering.
The automation of digital twinning for existing reinforced concrete bridges from point clouds remains an unresolved problem. Whilst current methods can automatically detect bridge objects in point clouds in the form of labelled point clusters, the fitting of accurate 3D shapes to point clusters remains largely human dependent largely. 95% of the total manual modelling time is spent on customizing shapes and fitting them correctly. The challenges exhibited in the fitting step are due to the irregular geometries of existing bridges. Existing methods can fit geometric primitives such as cuboids and cylinders to point clusters, assuming bridges are comprised of generic shapes. However, the produced geometric digital twins are too ideal to depict the real geometry of bridges. In addition, none of the existing methods have explicitly demonstrated how to evaluate the resulting Industry Foundation Classes bridge data models in terms of spatial accuracy using quantitative measurements. In this article, we tackle these challenges by delivering a slicing-based object fitting method that can generate the geometric digital twin of an existing reinforced concrete bridge from four types of labelled point cluster. The quality of the generated models is gauged using cloud-to-cloud distance-based metrics. Experiments on ten bridge point cloud datasets indicate that the method achieves an average modelling distance of 7.05 cm (while the manual method achieves 7.69 cm), and an average modelling time of 37.8 seconds. This is a huge leap over the current practice of digital twinning performed manually.
This paper takes a longitudinal view of literature to explain the current period as disruptive technology drives an evolutionary adaptation of the construction industry in a historical socio-technological process. The authors argue the way Internet of Things (IoT) solutions are conceived as singularly focused “point solutions” undermine future opportunities. An evolutionary view is overlooked because extant literature describes technology in a particular epoch. An ecosystem perspective needs to influence IT strategy as an emerging “digital layer” transcends a smart city and continues to function long after a traditional construction project completes. We describe innovation as a succession of transformational waves in an evolutionary process that is currently manifesting as “Industry 4.0” and changing expectations for the construction industry. The paper concludes by listing emerging trends and warns existing UK construction companies must understand the transformational process they are in and learn how to adapt with a stronger drive for R&D.
We address the problem of hole filling in depth images, obtained from either active or stereo sensing, for the purposes of depth image completion in an exemplar-based framework. Most existing exemplar-based inpainting techniques, designed for color image completion, do not perform well on depth information with object boundaries obstructed or surrounded by missing regions. In the proposed method, using both color (RGB) and depth (D) information available from a common-place RGB-D image, we explicitly modify the patch prioritization term utilized for target patch ordering to facilitate improved propagation of complex texture and linear structures within depth completion. Furthermore, the query space in the source region is constrained to increase the efficiency of the approach compared to other exemplar-driven methods. Evaluations demonstrate the efficacy of the proposed method compared to other contemporary completion techniques.
Vision-based monitoring methods have been actively studied in the construction industry because they can be used to automatically generate information related to progress, productivity, and safety. Object detection is essentially used in such monitoring methods to infer jobsite context. However, as many classes of construction entities exist in a job site, large amounts of image data are required to train a detection algorithm to detect each class object in images. Although image data augmentation methods using 3D models were proposed, publicly available 3D models are limited to some construction object classes. Therefore, this study proposes a three-dimensional reconstruction method to generate the image data required for training object detectors. To use the generated synthetic images as training data, a histogram of oriented gradient (HOG) descriptor of a target object is obtained from these images. The descriptor is refined by a support vector machine to increase sensitivity to the target object in test images. The performance of the HOG-based object detector is evaluated using real images from ImageNet. The result shows that the proposed method can generate training data more effectively than existing manual data collection practices.
Information and communications technology (ICT) has had major effects on the architecture, engineering, and construction (AEC) research fields in recent decades, but a comprehensive and in-depth review of how ICT has been used to enable different modes of information flow on project sites is missing from the current literature. To fill this gap, this paper defines a systematic approach for classifying information flow modes and uses this method to determine trends in information communication modes reported in recent publications. These trends were determined through the identification and analysis of 119 journal articles published between 2005 and 2015 in order to determine the mode of information flow reported. The results show that the majority of papers (70.6%) report a unidirectional flow of information, while a much smaller portion report one of two bidirectional information flow modes (26.9% non-automated, and 2.5% automated). The contribution of this work is in systematically defining current trends in ICT publications related to information flow and also in the identification of the typical technologies used to enable these communication modes.
The ever increasing volume of visual data due to recent advances in smart devices and camera-equipped platforms provides an unprecedented opportunity to visually capture actual status of construction sites at a fraction of cost compared to other alternatives methods. Most efforts on documenting as-built status, however, stay at collecting visual data and updating BIM. Hundreds of images and videos are captured but most of them soon become useless without properly being localized with plan document and time. To take full advantage of visual data for construction performance analytics, three aspects (reliability, relevance, and speed) of capturing, analyzing, and reporting visual data are critical. This paper 1) investigates current strategies for leveraging emerging big visual data and BIM in construction performance monitoring from these three aspects, 2) characterizes gaps in knowledge via case studies and structures a road map for research in visual sensing and analytics.
In this paper, a new methodology called Distributed Augmented Reality for Visualising Collaborative Construction Tasks (DARCC) is proposed. Using this methodology, virtual models of construction equipment can be operated and viewed by several operators to interactively simulate construction activities on the construction site in augmented reality mode. The chapter investigates the design issues of DARCC including tracking and registration, object modelling, engineering constraints, and interaction and communication methods. The DARCC methodology is implemented in a prototype system and tested through a case study of a bridge deck rehabilitation project.
The recognition of construction equipment is always necessary and important to monitor the progress and the safety of a construction project. Recently, the potentials of computer vision (CV) techniques have been investigated to facilitate the current equipment recognition method. However, the process of manually collecting and annotating a large image dataset of different equipment is one of the most time-consuming tasks that may delay the application of the CV techniques for construction equipment recognition. Moreover, collecting effective negative samples brings more difficulties for training the object detectors. This research aims to introduce an automated method for creating and annotating synthetic images of construction equipment while significantly reducing the required time. The synthetic images of the equipment are created from the three-dimensional (3D) models of construction machines combined with various background images taken from construction sites. The location of the equipment in the images is known since that equipment is the only object over the single-color background. This location can be extracted by applying segmentation techniques and then used for the annotation purpose. Furthermore, an automated negative image sampler is introduced in this paper to automatically generate many negative samples with different sizes out of one general image of a construction site in a way that the samples do not include the target object. The test results show that the proposed method is able to reduce the required time for annotating the images in comparison with traditional annotation methods while improving the detection accuracy.
Digital images and video clips collected at construction jobsites are commonly used for extracting useful information. Exploring new applications for image processing techniques within the area of construction engineering and management is a steady growing field of research. One of the initial steps for various image processing applications is automatically detecting various types of construction materials on construction images. In this paper, the authors conducted a comparison study to evaluate the performance of different machine learning techniques for detection of three common categorists of building materials: Concrete, red brick, and OSB boards. The employed classifiers in this research are: Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Support Vector Machine (SVM). To achieve this goal, the feature vectors extracted from image blocks are classified to perform a comparison between the efficiency of these methods for building material detection. The results indicate that for all three types of materials, SVM outperformed the other two techniques in terms of accurately detecting the material textures in images. The results also reveals that the common material detection algorithms perform very well in cases of detecting materials with distinct color and appearance (e.g., red brick); while their performance for detecting materials with color and texture variance (e.g., concrete) as well as materials containing similar color and appearance properties with other elements of the scene (e.g., ORB boards) might be less accurate. © 2015 Korean Society of Civil Engineers and Springer-Verlag Berlin Heidelberg