Conference Paper

Surface Distresses Detection of Pavement Based on Digital Image Processing

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Pavement crack is the main form of early diseases of pavement. The use of digital photography to record pavement images and subsequent crack detection and classification has undergone continuous improvements over the past decade. Digital image processing has been applied to detect the pavement crack for its advantages of large amount of information and automatic detection. The applications of digital image processing in pavement crack detection, distresses classification and evaluation were reviewed in the paper. The key problems were analyzed, such as image enhancement, image segmentation and edge detection. The experiment results of the commonly used algorithms forcefully supported following conclusion: the noise in pavement crack images is effectively removed by median filtering, the histogram modification technique is a useable segmentation approach, the canny edge detection is an ideal identification approach of pavement distresses.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Manual inspection is the dominant technique for pavement distress identification [3]. However, manual inspection can be labor-intensive, costly, and time-consuming. ...
... Also, the cosine learning rate is used [37]. In the beginning of training for the first few epochs (3)(4)(5) learning rate increases gradually to the desired point, and from epoch 5 to the end of the training process learning rate decreases gradually in a cosine form. In addition, learning rate noises applied to 30% and 90% of the training process. ...
Conference Paper
Full-text available
Pavement condition evaluation is essential to time the preventative or rehabilitative actions and control distress propagation. Failing to conduct timely evaluations can lead to severe structural and financial loss of the infrastructure and complete reconstructions. Automated computer-aided surveying measures can provide a database of road damage patterns and their locations. This database can be utilized for timely road repairs to gain the minimum cost of maintenance and the asphalt's maximum durability. This paper introduces a deep learning-based surveying scheme to analyze the image-based distress data in real-time. A database consisting of a diverse population of crack distress types such as longitudinal, transverse, and alligator cracks, photographed using mobile-device is used. Then, a family of efficient and scalable models that are tuned for pavement crack detection is trained. Proposed models, resulted in F1-scores, ranging from 52% to 56%, and average inference time from 178-10 images per second. Finally, the performance of the object detectors are examined, and error analysis is reported against various images. The source code is available at https://github.com/mahdi65/roadDamageDetection2020.
... Manual inspection is the dominant technique for pavement distress identification [3]. However, manual inspection can be labor-intensive, costly, and time-consuming. ...
... Also, the cosine learning rate is used [37]. In the beginning of training for the first few epochs (3)(4)(5) learning rate increases gradually to the desired point, and from epoch 5 to the end of the training process learning rate decreases gradually in a cosine form. In addition, learning rate noises applied to 30% and 90% of the training process. ...
Preprint
Full-text available
Pavement condition evaluation is essential to time the preventative or rehabilitative actions and control distress propagation. Failing to conduct timely evaluations can lead to severe structural and financial loss of the infrastructure and complete reconstructions. Automated computer-aided surveying measures can provide a database of road damage patterns and their locations. This database can be utilized for timely road repairs to gain the minimum cost of maintenance and the asphalt's maximum durability. This paper introduces a deep learning-based surveying scheme to analyze the image-based distress data in real-time. A database consisting of a diverse population of crack distress types such as longitudinal, transverse, and alligator cracks, photographed using mobile-device is used. Then, a family of efficient and scalable models that are tuned for pavement crack detection is trained. Proposed models, resulted in F1-scores, ranging from 52% to 56%, and average inference time from 178-10 images per second. Finally, the performance of the object detectors are examined, and error analysis is reported against various images. The source code is available at https://github.com/mahdi65/roadDamageDetection2020.
... Grieta procesada a partir de un filtro de mediana y posteriormente a partir de un algoritmo de borde(Ouyang et al., 2011) ...
... La aplicación de filtros de mediana es una de las técnicas más utilizadas para la mejora de imágenes de pavimentos. Esta técnica permite homogenizar todos aquellos pixeles de una imagen que cuentan con niveles de gris muy distintos a sus pixeles adyacentes(Ouyang et al., 2011).Una de las principales ventajas que trae consigo la aplicación de filtros de mediana, es el hecho de que esta técnica permite mejorar la imagen sin la necesidad de eliminar sus bordes o principales rasgos, permitiendo su posterior análisis (Chandel y Gupta 2013). Adicionalmente, a pesar de que el fundamento teórico de esta técnica puede ser complejo, actualmente hay muchos programas computacionales que permiten realizar este trabajo a partir de funciones preprogramadas. ...
Article
Full-text available
La atención oportuna de un sistema de carreteras mediante actividades de mantenimiento rutinario, como la construcción de baches y el sellado de grietas, es una práctica reconocida por su buena relación costobeneficio, al evitar que el pavimento se deteriore aceleradamente por el efecto del clima y del tránsito, reduciendo la necesidad de realizar intervenciones mayores y costosas. Sin embargo, pese a que las actividades de mantenimiento rutinario pueden ser muy beneficiosas, en Costa Rica, identificar los puntos en carretera que requieren ser atendidos mediante este tipo de intervenciones es una labor que está sesgada al criterio de quien realiza la auscultación visual de deterioros, y dependiendo de la ruta que está siendo evaluada podría ser una actividad peligrosa en términos de seguridad vial y seguridad ciudadana si se consideran zonas de riesgo social. Ante este panorama, se requiere contar con procesos automatizados que permitan generar un inventario de necesidades de mantenimiento de una manera ágil, objetiva y segura. Para ello, actualmente existen diversas alternativas que permiten automatizar el recuento de necesidades de mantenimiento preventivo de una carretera, siendo el procesamiento digital de imágenes una de las más útiles para este fin. El procesamiento digital de imágenes permite, mediante el uso de algoritmos aplicados a un registro fotográfico de la carretera, definir criterios de intervención para las actividades de mantenimiento rutinario. Lo anterior, con el objetivo de identificar con mayor certeza los deterioros bajo cierto umbral de severidad presentes en una carretera. De este modo, el registro digital de imágenes podría considerarse como un insumo muy valioso para mejorar la eficiencia en cuanto a la inversión ejecutada en un determinado sistema de carreteras, sin olvidar que este tipo de herramientas constituyen un complemento que no debe reemplazar el criterio técnico de los profesionales a cargo delagestión del sistema.
... Grieta procesada a partir de un filtro de mediana y posteriormente a partir de un algoritmo de borde(Ouyang et al., 2011) ...
... La aplicación de filtros de mediana es una de las técnicas más utilizadas para la mejora de imágenes de pavimentos. Esta técnica permite homogenizar todos aquellos pixeles de una imagen que cuentan con niveles de gris muy distintos a sus pixeles adyacentes(Ouyang et al., 2011).Una de las principales ventajas que trae consigo la aplicación de filtros de mediana, es el hecho de que esta técnica permite mejorar la imagen sin la necesidad de eliminar sus bordes o principales rasgos, permitiendo su posterior análisis (Chandel y Gupta 2013). Adicionalmente, a pesar de que el fundamento teórico de esta técnica puede ser complejo, actualmente hay muchos programas computacionales que permiten realizar este trabajo a partir de funciones preprogramadas. ...
Article
Full-text available
The timely attention of a road system through minor maintenance activities, such as potholes repair techniques and crack sealing, is a practice recognized for its good cost-benefit ratio, by preventing the pavement from an accelerated deterioration dueto the effect of climate and transit, reducing the need of major and expensive interventions. However, although minor maintenance activities can be very beneficial, in Costa Rica, identifying road segments that requirethesetypes of interventions is a work that could be biased to the criteriaof those who perform the visual auscultation of deteriorations, and depending on the route that is being evaluated, it could be a dangerous activity in terms of road safety. Given this scenario, it is necessary to have automated processes that allow generating an inventory of preventive maintenance needs in an agile, objective and safe manner. To do this, there are currently several alternatives that allow automating the count of preventive maintenance needs of a road, being digital image processing one of the most used. The digital image processing allows, by using algorithms applied to a road photographic record, to define intervention criteria for minor maintenance activities, in order toidentify with greater certainty the deteriorations under a certain threshold of severity present in a road. In this way, the digital image registry could be considered as a very valuable input to improve efficiency in terms of the investment made in a certain road system, without forgetting that this type of tools are a complement that should not replace the technical criteria of the professionals in charge of the road management system.
... [3] Crack detection based on the Digital Image Processing. [5] Crack detection and classification on roads using Anisotropy measure. Crack detection and Classification using Neural Networks and Supervised Learning Algorithm. ...
... For image segmentation, they used histogram modification technique. [5] Suwarna Gothane, Dr. M. V. Sarode (2015) proposed that road networks are preserved if sufficient maintenance can be done at the proper time. Some types of distress on the road surface are potholes, cracks, patches, etc. ...
... A brief summary of literature review is presented in Table 1. Early studies concentrated on rule-based methods like image thresholding (Abbas and Ismael 2021;Cheng et al. 2003;Cheng and Miyojim 1998;Oliveira and Correia 2009;Mahler et al. 1991;Salari and Bao 2011) and edge detection (Santhi et al. 2012;Zhao et al. 2010;Wang and Li 2007a;Nhat-Duc et al. 2018;Ouyang et al. 2011;Tsai et al. 2010;Canny 1986). These methods categorize pixels into object (here distress) or background based on the gray scale of pixels. ...
Article
Full-text available
Maintaining safe and reliable roadway infrastructure is a critical challenge that demands constant monitoring and analysis of surface level pavement distresses. Typically, this maintenance involves identifying and quantifying various forms of road damage, such as cracks and potholes, which are indicative of the pavement’s overall health and safety. Recently, deep learning (DL) based automated methods have been recognized as the state-of-art for pavement distress analysis. These methods streamline the maintenance process through a two-step procedure: initially localizing areas of distress on the pavement (i.e., through object detection models) and subsequently performing pixel-level segmentation to quantify the severity of the damage (i.e., through an image segmentation model). However, the effectiveness of DL models is significantly hampered by feature-level distribution shift, a common problem where there is significant difference between training data and real-world data in terms of features like brightness, contrast, texture among other statistical features. This issue affects DL model’s generalization ability, limiting its accuracy on new or unseen data. This paper introduces an innovative and cost-effective approach to enhance model generalization in the context of pavement distress segmentation. The proposed solution centers around an unsupervised generative data augmentation strategy that transforms features of new or unseen data to align closely with the training dataset before performing distress segmentation. The framework’s effectiveness in improving pavement distress segmentation ability, is demonstrated through comparative analysis against traditional methods under varying distribution shift scenarios. Results indicate a significant improvement in segmentation accuracy, highlighting the potential of generative data augmentation strategy to address distribution shift challenges. This paves the way for future advancements in pavement distress analysis and model generalization.
... The concept involves simplifying a region into a graph-based representation by extracting its skeleton, which represents the set of points within a region that are equidistant from its boundary [25]. Skeletonization can be primarily achieved with two methods: incrementally thinning the region by morphological erosion while maintaining endpoints and connectivity (the so-called "topology-preserving thinning"), or by computing the medial axis of the region and adopting the medial axis transform introduced by Blum [26]. ...
Preprint
Full-text available
Over time, buildings inevitably experience physical and functional deterioration. Regular, accurate inspections are essential to ensure safety and functionality, helping to avert hazardous and uncomfortable conditions. Cracks, a common indicator of structural distress, also facilitate air infiltration due to pressure differences between the interior and exterior. The precise and efficient detection of cracks, along with the estimation of air infiltration through these cracks, is thus critical for civil engineering applications aimed at reducing energy consumption and enhancing indoor air quality. This paper introduces a novel image processing framework for the automatic detection of cracks in building envelopes, coupled with the measurement of indoor and outdoor air parameters, which could be used to assess crack size and to estimate air infiltration rates by using heat transfer and fluid mechanics formulas. A computer vision-based system for automatic crack detection is first developed by using the Python OpenCV library through binarization, Otsu's thresholding and Canny operator; geometric quantification of the cracks is then obtained via skeletonization, and the resulting morphological characteristics of the cracks are finally used to estimate airflow by using common fluid mechanics formulas.
... Therefore, crack detection is crucial for monitoring and maintaining pavement surfaces, ensuring the security of the drivers. However, if traditional human inspection procedures are used, crack detection can be extremely tedious, time-consuming, and subjective [2]. Implementing automatic pavement condition monitoring systems can overcome these limitations, allowing a more precise, faster, and safer analysis than traditional methods, minimizing experts' effort and human subjectivity. ...
Article
Full-text available
Every day millions of people travel on highways for work- or leisure-related purposes. Ensuring road safety is thus of paramount importance, and maintaining good-quality road pavements is essential, requiring an effective maintenance policy. The automation of some road pavement maintenance tasks can reduce the time and effort required from experts. This paper proposes a simple system to help speed up road pavement surface inspection and its analysis towards making maintenance decisions. A low-cost video camera mounted on a vehicle was used to capture pavement imagery, which was fed to an automatic crack detection and classification system based on deep neural networks. The system provided two types of output: (i) a cracking percentage per road segment, providing an alert to areas that require attention from the experts; (ii) a segmentation map highlighting which areas of the road pavement surface are affected by cracking. With this data, it became possible to select which maintenance or rehabilitation processes the road pavement required. The system achieved promising results in the analysis of highway pavements, and being automated and having a low processing time, the system is expected to be an effective aid for experts dealing with road pavement maintenance.
... Thresholded images are divided into nonoverlapping blocks for entropy computation afterwards a second dynamic thresholding is applied to the resulting entropy blocks matrix, used as the basis for identification of image blocks containing crack pixels. [8]such as image enhancement, image segmentation and edge detection the noise in pavement crack images is effectively removed by median filtering, the histogram modification technique is a useable segmentation approach, and the canny edge detection is an ideal identification approach of pavement distresses. [9]developed an image processing technique that automatically detects and analyses cracks in the digital image of concrete surfaces is proposed. ...
Conference Paper
Full-text available
Road safety and pavement condition are considered a top priorities in our civilized societies, and it must begin and remain in an excellent condition for long time, but eventually the pavement will be exposed to many different types of distresses as a result of traffic loads, rough environment conditions, soil condition of the underline sub grade, so as to achieve the required standards for the pavement surface roads in our Libyan community, and provide the best performance, detection and measurements of distresses extension should be done in order to maintenance preparation. This paper proposes and developed a technique for the crack detection and width estimation based on digital image processing using a programming language called Matrix Laboratory known as MATLAB. ‫ﻋﻤﺮ‬ ‫و‬ ‫اﻟﻌﯿﺎط‬ ‫اﻹﻧﺸﺎﺋ‬ ‫واﻟﮭﻨﺪﺳﺔ‬ ‫اﻟﺒﻨﺎء‬ ‫ﻟﻤﻮاد‬ ‫اﻟﺘﺎﺳﻊ‬ ‫اﻟﻮطﻨﻲ‬ ‫اﻟﻤﺆﺗﻤﺮ‬ ‫ﯿﺔ‬ 2 ‫اﻟﻤﺪﻧﯿﺔ‬ ‫اﻟﮭﻨﺪﺳﺔ‬ ‫ﻗﺴﻢ‬-‫طﺮاﺑﻠﺲ‬ ‫ﺟﺎﻣﻌﺔ‬-‫ﻟﯿﺒﯿ‬ ‫ﺎ‬ ‫ﻋﺮﺿﮫ‬ ‫وﺗﻘﺪﯾﺮ‬ ‫اﻟﺮﺻﻒ‬ ‫ﺷﻘﻮق‬ ‫ﻛﺸﻒ‬ ‫ﺑ‬ ‫اﻟﺮﻗﻤﯿﺔ‬ ‫اﻟﺼﻮر‬ ‫ﻣﻌﺎﻟﺠﺔ‬ ‫ﺗﻘﻨﯿﺔ‬ ‫ﺎﺳﺘﺨﺪام‬ ‫اﻟﻌﯿﺎط‬ ‫ﺑﺸﯿﺮ‬ ‫ﻋﺒﺪاﻟﺴﻼم‬ 1 ، ‫ﻋﻠﻲ‬ ‫ﻋﻤﺮ‬ ‫ھﻨﺪ‬ 2 1 ‫اﻟﮭﻨﺪﺳﺔ‬ ‫ﻛﻠﯿﺔ‬ ‫اﻟﻤﺪﻧﯿﺔ‬ ‫اﻟﮭﻨﺪﺳﺔ‬ ‫ﻟﯿﺒﯿﺎ‬ ‫طﺮاﺑﻠﺲ،‬ ‫ﺟﺎﻣﻌﺔ‬ 2 ‫اﻟﮭﻨﺪﺳﺔ‬ ‫ﻛﻠﯿﺔ‬ ‫اﻟﻤﺪﻧﯿﺔ‬ ‫اﻟﮭﻨﺪﺳﺔ‬ ‫ﻟﯿﺒﯿﺎ‬ ‫طﺮاﺑﻠﺲ،‬ ‫ﺟﺎﻣﻌﺔ‬ ‫ﻣﻠﺨﺺ‬ ‫ﺑﺤﺎﻟﺔ‬ ‫وﺗﺒﻘﻰ‬ ‫ﺗﺒﺪأ‬ ‫أن‬ ‫وﯾﺠﺐ‬ ‫اﻟﻤﺘﺤﻀﺮة،‬ ‫ﻣﺠﺘﻤﻌﺎﺗﻨﺎ‬ ‫ﻓﻲ‬ ‫اﻟﻘﺼﻮى‬ ‫اﻷوﻟﻮﯾﺎت‬ ‫ﻣﻦ‬ ‫واﻷرﺻﻔﺔ‬ ‫اﻟﻄﺮق‬ ‫ﻋﻠﻰ‬ ‫اﻟﺴﻼﻣﺔ‬ ‫ﺣﺎﻟﺔ‬ ‫ﺗﻌﺘﺒﺮ‬ ‫اﻟ‬ ‫أﻧﻮاع‬ ‫ﻣﻦ‬ ‫ﻟﻠﻌﺪﯾﺪ‬ ‫اﻟﺮﺻﻒ‬ ‫ﺳﯿﺘﻌﺮض‬ ‫اﻟﻨﮭﺎﯾﺔ‬ ‫ﻓﻲ‬ ‫وﻟﻜﻦ‬ ‫طﻮﯾﻠﺔ،‬ ‫ﻟﻔﺘﺮة‬ ‫ﻣﻤﺘﺎزة‬ ‫ﺸﻘﻮق‬ ‫اﻟﻤﺮورﯾﺔ‬ ‫اﻷﺣﻤﺎل‬ ‫ﻧﺘﯿﺠﺔ‬ ‫اﻟﻤﺨﺘﻠﻔﺔ‬ ‫ﻓﻲ‬ ‫اﻟﺘﺮﺑﺔ‬ ‫وﺣﺎﻟﺔ‬ ‫اﻟﺒﯿﺌﯿﺔ،‬ ‫اﻟﻈﺮوف‬ ‫اﻟﻘﺎﺳﯿﺔ.‬ ‫اﻟﺮﺻﻒ‬ ‫ﻟﻄﺮق‬ ‫اﻟﻤﻄﻠﻮﺑﺔ‬ ‫اﻟﻤﻌﺎﯾﯿﺮ‬ ‫ﻟﺘﺤﻘﯿﻖ‬ ‫وذﻟﻚ‬ ‫اﻟﺴﻔﻠﯿﺔ،‬ ‫اﻟﻔﺮﻋﯿﺔ‬ ‫اﻟﻄﺒﻘﺔ‬ ‫اﻣﺘﺪاد‬ ‫وﻗﯿﺎﺳﺎت‬ ‫واﻛﺘﺸﺎف‬ ‫أداء‬ ‫أﻓﻀﻞ‬ ‫وﺗﻘﺪﯾﻢ‬ ، ‫اﻟﻠﯿﺒﻲ‬ ‫ﻣﺠﺘﻤﻌﻨﺎ‬ ‫ﻓﻲ‬ ‫اﻟﺴﻄﺤﯿﺔ‬ ‫اﻟﺸﻘﻮق‬ ‫ﯾﻘﺘﺮح‬ ‫ﻟﻠﺼﯿﺎﻧﺔ.‬ ‫اﻹﻋﺪاد‬ ‫أﺟﻞ‬ ‫ﻣﻦ‬ ‫وذﻟﻚ‬ ، ‫اﻟﺮﻗﻤﯿﺔ‬ ‫اﻟﺼﻮر‬ ‫ﻣﻌﺎﻟﺠﺔ‬ ‫ﻋﻠﻰ‬ ً ‫ﺑﻨﺎء‬ ‫اﻟﻌﺮض‬ ‫وﺗﻘﺪﯾﺮ‬ ‫اﻟﺸﻘﻮق‬ ‫ﻻﻛﺘﺸﺎف‬ ‫ﺗﻘﻨﯿﺔ‬ ‫وﯾﻄﻮر‬ ‫اﻟﺒﺤﺚ‬ ‫ھﺬا‬ ‫ﺗﺴﻤﻰ‬ ‫ﺑﺮﻣﺠﺔ‬ ‫ﻟﻐﺔ‬ ‫ﺑﺎﺳﺘﺨﺪام‬ Matrix Laboratory ‫ﺑﺎﺳﻢ‬ ‫اﻟﻤﻌﺮوف‬ MATLAB .
... Image pre-processing mostly deals with noise shadow and removing unnecessary information (through cropped images) from the captured images. Due to these obstacles, different preprocessing methods for contrast enhancement [42,58], like filtering [44] and smoothing, are used for image quality enhancement. Ouyang et al. [9] proposed a pre-processing method with three essential steps: Median filtering is used to eliminate noise, image segmentation done by modification in the histogram, and edge detection methods, finally differentiate the crack edges from the image. ...
Article
Full-text available
Automatic crack detection is a challenging task that has been researched for decades due to the complex civil structures. Cracks on any structure are early signs of the deterioration of the object’s surface. Therefore, detection and regular maintenance of cracks are necessary tasks as the propagation of cracks results in severe damage. Manual inspection is based on the expert’s previous knowledge, and it can only be done in reachable human areas. On the other hand, autonomous detection of cracks by using image-based techniques may reduce human errors, less time-consuming, and more economical than human-based inspection for real-time crack detection. Since movable cameras can capture images for non-reachable areas, several techniques are available for crack detection. Several techniques are available for crack detection; however, image-based crack detection techniques have been analyzed in this survey. A detailed study is carried out to define the research problems and advancements in this area. This article analyses the pure image processing techniques and learning-based techniques based on the objectives, the methods, level of efficiency, level of errors, and type of crack image dataset. Besides the applications, limitations and other factors are explained for each technique. Moreover, the presented analysis shows the multiple problems related to cracks that could help the researcher perform further research.
... Given the detection framework in identifying the shapes of the objects, canny edge detection tends to play a role in analyzing the pavement distress. Which includes, moving pavement distress classification (Zhao, Qin, and Wang 2010), pavement crack measurement (Ouyang, Luo, and Zhou 2011), classifying the pavement distress based on edges (Santhi et al. 2012), pavement distress through mobile mapping (Mancini et al. 2013), application of supervised machine learning to map the distress (Nguyen, Zhukov, and Nguyen 2016), pothole mapping over the road space(Q. Li et al. 2009), Feeding the detected edges to neurons in deep learning to classify the pavement distress (Nhat-Duc, Nguyen, and Tran 2018). ...
Preprint
Full-text available
The article presents a literature review on the current existing advanced pavement distress measuring methodologies. In line with that, five image processing techniques and 3D scanning practices are reviewed, and their application is explained in the present-day context. It is identified that researchers found to be heavily dependent on image processing techniques to develop automated distress measurement techniques in the present context. However, at the same time, the limitations of the image processing techniques were found to act as a constraint in this direction. It is found that the surface texture of the pavement plays a significant role in measuring the pavement distress from image processing techniques. Due to this, the efficiency of the image processing techniques tends to vary with the distress patterns. On the other hand, the 3D scanning practices were found to have massive scope in these directions from the literature. Further, a literature review analysis is performed in that pavement distress is classified and compared with the literature of the reviewed methods.
... This can reduce image noise and hence improve the crack detection results. Pre-processing steps may include median filters, opening and closing morphological filters to join crack segments [20][21][22][23]. ...
Article
Full-text available
A variety of civil engineering applications require the identification of cracks in roads and buildings. In such cases, it is frequently helpful for the precise location of cracks to be identified as labelled parts within an image to facilitate precision repair for example. CrackIT is known as a crack detection algorithm that allows a user to choose between a block-based or a pixel-based approach. The block-based approach is noise-tolerant but is not accurate in edge localization while the pixel-based approach gives accurate edge localisation but is not noise-tolerant. We propose a new approach that combines both techniques and retains the advantages of each. The new method is evaluated on three standard crack image datasets. The method was compared with the CrackIT method and three deep learning methods namely, HED, RCF and the FPHB. The new approach outperformed the existing arts and reduced the discretisation errors significantly while still being noise-tolerant.
... Two-dimensional or three-dimensional images and videos are also harnessed in the field of pavement distress detection. Georgopoulos, Loizos, & Fiouda, Ho et al. and Ouyang, Luo, and Zhou, employed digital image processing technique to automatically and objectively determine the type, extent, and severity of cracks on flexible pavements [18][19][20]. Nienaber, Booysen, and Kroon, and Vigneshwar and Kumar, utilized simple image processing techniques and real-world footages to detect the potholes present on the pavement [21,22]. Lokeshwor, Das, and Goel employed video processing for detecting and quantifying pavement distresses [23,24]. ...
Article
Roads are the largest component of infrastructure; they directly impact people’s life by providing mobility and connectivity. To ensure consistent surface quality, roads must be monitored continuously and repaired when necessary. Presently, authorities spend substantial amount of time, finance and labor for pavement distress detection by employing traditional manual and instrumented methods which are generally tedious, and time-consuming. To overcome these drawbacks, various automated techniques like Ground Penetrating Radar, Laser-Imaging-Systems, etc. are deployed. Recently, image-processing and smartphone-based systems are being devised for pavement distress detection. Here, a vibration-based method using smartphone accelerometer and gyroscope, and a vision-based method using video processing for automated pavement distress detection are designed and compared to identify the more suitable one. Both experiments are performed on same roads and results are validated by manual surveying. Accuracy of vibration-based method for detecting potholes, patches and bumps is found as 80%. Accuracy for detecting cracks, potholes and patches using vision-based method is identified as 84%. An additional effort is taken to estimate the extent of pavement distresses using vision-based approach and validate it using manual stripping method. The study reveals that, vibration-based-analysis is sufficient for routine monitoring purposes whereas vision-based-method is more appropriate for detailed analysis.
... Poor road conditions also lead to excessive wear on vehicles and tend to increase the number of delays and crashes which can lead to additional financial losses [3]. Currently, manual inspection is the most common technique for identifying pavement distress road surveys [4]. Manual inspection can be, however, time-consuming, costly, and labor-intensive. ...
Article
Full-text available
Pavement surveying and distress mapping is completed by roadway authorities to quantify the topical and structural damage levels for strategic preventative or rehabilitative action. The failure to time the preventative or rehabilitative action and control distress propagation can lead to severe structural and financial loss of the asset requiring complete reconstruction. Continuous and computer-aided surveying measures not only can eliminate human error when analyzing, identifying, defining, and mapping pavement surface distresses, but also can provide a database of road damage patterns and their locations. The database can be used for timely road repairs to gain the maximum durability of the asphalt and the minimum cost of maintenance. This paper introduces an autonomous surveying scheme to collect, analyze, and map the image-based distress data in real time. A descriptive approach is considered for identifying cracks from collected images using a convolutional neural network (CNN) that classifies several types of cracks. Typically, CNN-based schemes require a relatively large processing power to detect desired objects in images in real time. However, the portability objective of this work requires to utilize low-weight processing units. To that end, the CNN training was optimized by the Bayesian optimization algorithm (BOA) to achieve the maximum accuracy and minimum processing time with minimum neural network layers. First, a database consisting of a diverse population of crack distress types such as longitudinal, transverse, and alligator cracks, photographed at multiple angles, was prepared. Then, the database was used to train a CNN whose hyperparameters were optimized using BOA. Finally, a heuristic algorithm is introduced to process the CNN’s output and produce the crack map. The performance of the classifier and mapping algorithm is examined against still images and videos captured by a drone from cracked pavement. In both instances, the proposed CNN was able to classify the cracks with 97% accuracy. The mapping algorithm is able to map a diverse population of surface cracks patterns in real time at the speed of 11.1 km per hour.
... The derivation of cracking from pavement images has been widely discussed in the literature (Chambon and Moliard, 2011;Ouyang et al., 2011;Tsai et al., 2010), with numerous schemes proposed for the assessment of cracks, as well as for assessing the relative benefits of those schemes. In addition to crack analysis, several groups have investigated the use of pavement images in the assessment of pavement texture. ...
Article
Full-text available
Over the last 20 years road pavement imaging has become a routine output from annual pavement assessment survey regimes across the world. Hitherto the traditional use of road pavement images in road condition assessment has been crack detection, rather than direct analysis of image features such as aggregate loss, changes in surface texture or deterioration of road markings. Any attempt to assess pavement condition change from features in a sequence of such images captured months or years apart requires image registration. A method for registering road pavement images is presented that makes use of an affine transformation based on pseudo-features within images. An affine transformation is considered suitable for registering road pavement images because of the linear way in which pavements are surveyed. Pseudo feature points are found using a modified corner detector, and then matching points between reference and template images established via a correlation analysis of pavement image texture. With 4 such points it is possible to establish an affine transformation between the images. The method is tested on pavement images captured on three UK sites between winter 2014/15 and 2015/16. The method successfully registered 98% of images captured on sites typical of the UK's strategic road network, and 65% of images captured on a site typical of the UK's minor road network.
... Ouyang et al. [21] made a very interesting preprocessing of crack images. They divide the process in three main steps: image enhancement using median filtering to remove noise, image segmentation using a histogram modification technique, and Canny edge detection to finally distinguish crack edges from the rest of the image. ...
Article
Full-text available
Each year, millions of dollars are invested on road maintenance and reparation all over the world. In order to minimize costs, one of the main aspects is the early detection of those flaws. Different types of cracks require different types of repairs; therefore, not only a crack detection is required but a crack type classification. Also, the earlier the crack is detected, the cheaper the reparation is. Once the images are captured, several processes are applied in order to extract the main characteristics for emphasizing the cracks (logarithmic transformation, bilateral filter, Canny algorithm, and a morphological filter). After image preprocessing, a decision tree heuristic algorithm is applied to finally classify the image. This work obtained an average of 88% of success detecting cracks and an 80% of success detecting the type of the crack. It could be implemented in a vehicle traveling as fast as 130 kmh or 81 mph.
... To detect the pavement distresses on images, Ouyang, et al. tried an approach based on filtering the images to remove the background or pavement texture, image enhancements, segmentation and Canny edge detection [6]. ...
Article
Full-text available
An accurate and regular survey of the road surface distresses is a key factor for pavement rehabilitation design and management, allowing public managers to maximize the value of the continuously limited budgets for road improvements and maintenance. Manual pavement distress surveys are labor-intensive, expensive and unsafe for highly-trafficked highways. Over the years, automated surveys using various hardware devices have been developed and improved for pavement field data collection to solve the problems associated with manual surveys. However, the reliable distress detection software and the data analysis remain challenging. This study focused on the analysis of a newly-developed pavement distress classification algorithm, called the PICture Unsupervised Classification with Human Analysis (PICUCHA) method, particularly the impact of image resolutions on its classification accuracy. The results show that a non-linear relationship exists between the classification accuracy and the image resolution, suggesting that images with a resolution around 1.24 mm/pixel may provide the optimal classification accuracy when using the PICUCHA method. The findings of this study can help to improve more effective uses of the specialize software for pavement distress classification, to support decision makers to choose cameras according to their budgets and desired survey accuracy, and to evaluate how existing cameras will perform if used with PICUCHA.
... In the past two decades, several methods [3][4][5][6][7][8][9][10][11][12] based on digital image processing have been proposed for pavement distress detection. Hu et al. [5] proposed an approach for pavement distress detection by using texture analysis and shape descriptors by utilizing the gray-level co-occurrence matrix (GLCM) in order to extract the features used for texture recognition and classification. ...
Article
Full-text available
Pavement condition assessment plays an important role in the process of road maintenance and rehabilitation. However, the traditional road inspection procedure is mostly performed manually, which is labor-intensive and time-consuming. The development of automated detection and classification of distress on the pavement surface system is thus necessary. In this paper, a pavement surface distress detection and classification system using a hybrid between the artificial bee colony (ABC) algorithm and an artificial neural network (ANN), called “ABC-ANN”, is proposed. In the proposed method, first, after the pavement image is captured, it will be segmented into distressed and non-distressed regions based on a thresholding method. The optimal threshold value used for segmentation in this step will be obtained from the ABC algorithm. Next, the features, including the vertical distress measure, the horizontal distress measure, and the total number of distress pixels, are extracted from a distressed region and used to provide the input to the ANN. Finally, based on these input features, the ANN will be employed to classify an area of distress as a specific type of distress, which includes transversal crack, longitudinal crack, and pothole. The experimental results demonstrate that the proposed approach works well for pavement distress detection and can classify distress types in pavement images with reasonable accuracy. The accuracy obtained by the proposed ABC-ANN method achieves 20 % increase compared with existing algorithms.
... However, this scheme depended excessively on prior information which rendered it incapable of handling the various shapes that cracks could assume owing to its inability to guarantee generalization. Based on digital image processing techniques, another approach is presented in [15] towards surface distress detection in pavements. This approach also relied excessively on traditional image processing techniques while failing to incorporate robust features into its framework. ...
... Two primary segmentation methods utilized for pavement distress identification are edge-detection and thresholding [100,115,127]. [61,101] applied edge-detection algorithms such as Canny and fast Haar tranforms for crack identification [17]. [68] utilized image segmentation and texture analysis to identify potholes. ...
Article
Full-text available
Introduction Evaluating the condition of transportation infrastructure is an expensive, labor intensive, and time consuming process. Many traditional road evaluation methods utilize measurements taken in situ along with visual examinations and interpretations. The measurement of damage and deterioration is often qualitative and limited to point observations. Remote sensing techniques offer nondestructive methods for road condition assessment with large spatial coverage. These tools provide an opportunity for frequent, comprehensive, and quantitative surveys of transportation infrastructure. Methods The goal of this paper is to provide a bridge between traditional procedures for road evaluation and remote sensing methodologies by creating a comprehensive reference for geotechnical engineers and remote sensing experts alike. Results A comprehensive literature review and survey of current techniques and research methods is provided to facilitate this bridge. A special emphasis is given to the challenges associated with transportation assessment in the aftermath of major disasters. Conclusions The use of remote sensing techniques offers new potential for pavement managers to assess large areas, often in little time. Although remote sensing techniques can never entirely replace traditional geotechnical methods, they do provide an opportunity to reduce the number or size of areas requiring site visits or manual methods.
... It is estimated that pavement distresses cause damage costing $10 billion each year in the United States alone [2]. Technically, cracks are the main form of early pavement diseases [3]. Unfortunately, if these early distresses were not treated, potholes are formed causing the pavement to become more dangerous. ...
Conference Paper
Full-text available
Pavement condition evaluation is a significant part of a good pavement management system for effective maintenance, rehabilitation, and reconstruction decision-making. One of the key components of pavement condition evaluation is the quantification of pavement distresses data. Cracking is the main form of early pavement distresses. Cracking of pavement affects road condition, driving comfort, traffic safety, and consequently reduce pavement service life. Once initiated, cracking increases in extent and severity and accordingly accelerates the rate of pavement deterioration. Therefore, the awareness about crack type, extent, and severity is essential to evaluate pavement condition and to determine timing and cost of pavement maintenance. Digital image-based automated pavement evaluation has been gradually replacing the manual pavement evaluation due to its improved efficiency and safely operating. In this paper, we are presenting a novel reliable automated pavement assessment system based on image processing techniques and machine learning methods. The proposed system has the ability to i) identify crack, ii) extract crack parameters, and iii) report the type, extent, and severity level of that crack in an output file. Actual pavement images were used to verify the performance of the proposed system. The results clearly demonstrated that the proposed system was able to automatically and effectively identify crack type and efficiently extract crack parameters from pavement images. Such information can be used by public road agencies to define maintenance plans and assist in pavement management decision-making, in accordance with real pavement condition.
Preprint
Full-text available
Maintaining safe and reliable roadway infrastructure is a critical challenge that demands constant monitoring and analysis of surface level pavement distresses. Typically, this maintenance involves identifying and quantifying various forms of road damage, such as cracks and potholes, which are indicative of the pavement's overall health and safety. Recently, deep learning (DL) based automated methods have been recognized as the state-of-art for pavement distress analysis. These methods streamline the maintenance process through a two-step procedure: initially localizing areas of distress on the pavement (i.e., through object detection models) and subsequently performing pixel-level segmentation to quantify the severity of the damage (i.e., through an image segmentation model). However, the effectiveness of DL models is significantly hampered by feature-level distribution shift, a common problem where there is significant difference between training data and real-world data in terms of features like brightness, contrast, texture among other statistical features. This issue affects DL model's generalization ability, limiting its accuracy on new or unseen data. This paper introduces an innovative and cost-effective approach to enhance model generalization in the context of pavement distress segmentation. The proposed solution centers around an unsupervised generative data augmentation strategy that transforms features of new or unseen data to align closely with the training dataset before performing distress segmentation. The framework's effectiveness in improving pavement distress segmentation ability, is demonstrated through comparative analysis against traditional methods under varying distribution shift scenarios. Results indicate a significant improvement in segmentation accuracy, highlighting the potential of generative data augmentation strategy to address distribution shift challenges. This paves the way for future advancements in pavement distress analysis and model generalization.
Article
Pavement evaluation helps assess the structural and functional condition of roads. Traditional pavement evaluation methods cannot efficiently and accurately assess the state of road conditions at the network level. Though the pavement evaluation techniques based on high-resolution cameras and laser sensors assess the road conditions efficiently at traffic speeds, there are a few limitations in respect of automotive detection and quantification of pavement surface distress. Though artificial intelligence is a broad area, machine learning applications in highway engineering were proven to be successful. This paper presents the automated pavement distress classification using a convolutional neural network (NN) from the Keras library. VGG-16, the deep convolutional NN (DCNN) model, was deployed by necessary modification to get the desired output. The model is trained on a big data set of images with a wide range of pavement defects and irregularities. A DCNN classifier trained with an “Adam” optimizer was used to change the features of the NN to minimize the loss. As an output, the model classifies the pavement surface distresses as alligator cracks, longitudinal cracks, transverse cracks, pothole, and no crack portion of the pavement with maximum accuracy using a DCNN classifier.
Article
Full-text available
As the most common method to detect pavement cracks, manual detection has uncontrollable factors such as low efficiency, inconsistent standards and easy to be interfered with by external forces, so it is not suitable for pavement crack detection in today’s intricate traffic network. In order to improve the efficiency of pavement repair and reduce the labor cost of the repair process, this paper proposes an intelligent pavement crack detection and repair algorithm. The algorithm uses image numerical parameters to classify cracks with different geometric features and extracts texture geometric features of various types of cracks based on different filtering strategies. It solves the problem that traditional single filtering algorithms are difficult to extract features according to the different characteristics of the collected image, which leads to the loss of information. Finally, the algorithm establishes a mathematical model for efficient trajectory planning combined with the nozzle size of the crack-repairing machine. In this paper, the robustness and efficiency test of the algorithm is carried out on the pavement image dataset with various types of cracks, and the experiment is carried out on the intelligent pavement crack detection and repair prototype, which verifies the accuracy and reliability of the planned trajectory.
Chapter
Timely detection of road cracks is vital for efficient maintenance of road pavements. The conventional road condition assessments involve manual surveys that fail to meet the present-day requirements. Hence, there arises a need to assess the pavement conditions using state-of-the-art technology. The presented work addresses this need and utilizes 2D-digital images of roads. The study considers Sobel edge detection operator and analyzes the performance of its components when used individually vis-à-vis when combined for recognizing road cracks. The main feature of this study is to establish a relation between the type of road crack to be recognized, the type of Sobel component to be used, and the direction and orientation of capturing road images. The study concludes by providing guidelines about which element of a Sobel operator is suitable for highlighting which crack type. The results are beneficial when crack highlighting is required at pixel level to provide more precise information about road damage and its severity.
Article
Full-text available
In real time scenario, cracks are very common in building, bridge, road, pavement, railway track, automobile, tunnel and aircraft. The presence of crack diminishes the value of the civil infrastructure and hence it is necessary to estimate the severity of crack. Crack detection and classification techniques with quantitative analysis play a major role in finding the severity of crack. The various quantitative metrics are length, width and area. Due to the rapid development in technology, number of images acquired for analysis is growing enormously. Therefore, automatic crack detection and classification techniques for civil infrastructure are essential. This paper focuses on three objectives:(i) Analysis of various crack detection and classification techniques based on crack types (ii) Implementation of Otsu’s based thresholding method for crack detection (iii) Design of proposed system.
Article
Full-text available
This paper presents an enhanced and robust approach to detect and classify pavement cracks from captured images. The approach was based on three stages: pre-processing, feature extraction and classification. In pre-processing, we carried out several algorithms to compensate the impact of quality distortions during image acquisition. Then, features are retrieved from projective integrals computed on edge images. These features fed machine learning algorithms to classify the type of crack that may appear in a pavement image. The obtained results proved the relevance of our reduced features. We achieved the best successful classification rate of 93.4% using the Support Vector Machine (SVM) classifier and an accuracy of 94.7% for crack detection.
Chapter
Early detection and measurement of the distresses are necessary to keep the pavement functions at an acceptable level and to pledge the safety users. The use of digital photography in order to record pavement images and, later, to identify the surface distresses has undergone continuous improvements during recent years. Image measurement methods are effortless, safe, and can be performed in a short time. In this paper, an image processing measurement is presented to locate potholes and cracks on the pavement surface through pictures by drone.
Article
Full-text available
The evaluation of pavement conditions is an important part of pavement management. Traditionally, pavement condition data are gathered by human inspectors who walk or drive along the road to assess the distresses and subsequently produce report sheets. This visual survey method is not only time consuming and costly but more importantly it compromises the safety of the field personnel. With an automated digital image processing technique, however, pavement distress analysis can be conducted in a swifter and safer manner. Pavement distresses are captured on images which are later automatically analysed. Furthermore, the automated method can improve the objectivity, accuracy, and consistency of the distress survey data. This research is aimed at the development of an Automated Pavement Imaging Program (APIP) for evaluating pavement distress condition. The digital image processing program enables longitudinal, transverse, and alligator cracking to be classified. Subsequently, the program will automatically estimate the crack intensity which can be used for rating pavement distress severity. Advancement in digital photogrammetric technology creates an opportunity to overcome some problems associated with the manual methods. It can provide a low-cost, near real time geometrical imaging through digital photogrammetry without physically touching the surface being measured. Moreover, digital photogrammetry workstation (DPW) is user-friendly, less tedious and enables surface conditions to be represented as ortho-image, overlay contour with ortho-image, as well as digital elevation model. The algorithms developed in this study are found to be capable of identifying type of cracking and its severity level with an accuracy of about 90% when compared to the traditional method. This is to show that the combination of the photogrammetric approach and APIP is a viable system to be used in pavement evaluations.
Article
Full-text available
Image segmentation is the crucial step in automatic image distress detection and classification (e.g., types and severities) and has important applications for automatic crack sealing. Although many researchers have developed pavement distress detection and recognition algorithms, full automation has remained a challenge. This is the first paper that uses a scoring measure to quantitatively and objectively evaluate the performance of six different segmentation algorithms. Up-to-date research on pavement distress detection and segmentation is comprehensively reviewed to identify the research need. Six segmentation methods are then tested using a diverse set of actual pavement images taken on interstate highway 1-75/I-85 near Atlanta and provided by the Georgia Department of Transportation with varying lighting conditions, shadows, and crack positions to differentiate their performance. The dynamic optimization-based method, which was previously used for segmenting low signal-to-noise ratio (SNR) digital radiography images, outperforms the other five methods based on our scoring measure. It is robust to image variations in our data set but the computation time required is high. By critically assessing the strengths and limitations of the existing algorithms, the paper provides valuable insight and guideline for future algorithm development that are important in automating image distress detection and classification.
Article
Full-text available
This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.
Book
Emphasizing sound, cost-effective management rather than emergency repairs, this comprehensive volume offers practical guidelines on evaluating and managing pavements for airports, municipalities, and commercial real estate firms. © 2005 Springer Science+Business Media, LLC. All rights reserved.
Conference Paper
In the paper, first the Algorithm of optimum threshold is used to remove the noise pixels of the pavement image, such as pavement marking image; Next the pavement image is divided into 400 subimages which has 100 x 100 pixels, the feature of pavement subimages are represented by gray variance, and the threshold of the good pavement subimages feature is found though the method of online learning, then the sub-images are made to do the image binarization. Finally, the counting feature of binary pavement image is used as the parameter to classify the pavement distress images, and searching pavement surface distress images are achieved.
Article
This paper presents the recent efforts in developing an image processing algorithm for computing a unified pavement crack index for Salt Lake City. The pavement surface images were collected using a digital camera mounted on a van. Each image covers a pavement area of 2.13 m (7 ft) × 1.52 m (5 ft), taken at every 30-m (100-ft) station. The digital images were then transferred onto a 1-gigabyte hard disk from a set of memory cards each of which can store 21 digital images. Approximately 1,500 images are then transferred from the hard disk to a compact disc. The image-processing algorithm, based on a variable thresholding technique, was developed on a personal computer to automatically process pavement images. The image is divided into 140 smaller tiles, each tile consisting of 40 × 40 pixels. To measure the amount of cracking, a variable threshold value is computed based on the average gray value of each tile. The program then automatically counts the number of cracked tiles and computes a unified crack index for each pavement image. The crack indexes computed from the image-processing algorithms are compared against the manual rating procedure in this paper. The image-processing algorithms were applied to process more than 450 surveyed miles of Salt Lake City street network.
Article
Statistics published by the Federal Highway Administration indicates that maintenance and rehabilitation of highway pavements in the United States requires over $17 billion a year. Conventional visual and manual pavement distress analysis approaches that the inspectors traverse the roads, stop and measure the distress objects when they are found, are very costly, time-consuming, dangerous, labor-intensive, tedious, subjective, having high degree of variability, unable to provide meaningful quantitative information, and almost always leading to inconsistencies in distress detail over space and across evaluations. This paper introduces a new pavement distress image enhancement algorithm, and a new analysis and classification algorithm. The enhancement algorithm corrects nonuniform background illumination by calculating multiplication factors that eliminate the background lighting variations. The new pavement distress classification algorithm builds a data structure storing the geometry of the skeleton obtained from the thresholded image. This data structure is pruned, simplified, and aligned, yielding a set of features for distress classification: number of distress objects, number of branch intersections, number of loops, relative sizes of branches in each direction, etc. This skeleton analysis algorithm relies on two-dimensional geometrical parameters, which are understandable by both developers and users, unlike some methods that deal with abstract quantities not readily understood by ordinary users. The proposed analysis algorithm can precisely quantify geometrical and topological parameters, can quickly accept new classification rules for classification, and can estimate the distress severity from the thresholded image. The experimental results are satisfactory.
Article
Graduation date: 1998 The evaluation of pavement condition is an important part of pavement management. To evaluate a pavement, a distress survey has been performed mainly by manual field inspections. Several automatic pavement evaluation systems have been developed to overcome the drawbacks of field inspections. Automated evaluation systems, however, imply their own limitations in terms of cost, technical problems, and adaptability for pavement management. The main purpose of this research is to develop a low-cost automatic pavement video imaging system. The secondary purpose is the development of techniques to process the collected video images. A low-cost video image-collection system and an in-office system were developed. A video test was implemented on a selected route including various pavement types and several variables. As a result of the test, seven loop tests provided acceptable results to allow image analysis. By using the video camera with fast shutter-speed, it was decided that the survey vehicle could drive at high speed (65mph) while maintaining good picture quality. To evaluate the performance of the system, video and field inspections were performed using two approaches: the Oregon Department of Transportation (ODOT) and Metropolitan Transportation Commissions (MTC) approaches. The inspections were conducted on 107 sample sections. Also, sample still images were digitized for analysis. To conduct a video inspection, the Global Positioning System (GPS) technique was applied for conversion of video mileage to real field mileage. The results of video and field inspections were compared using statistical analyses. The ODOT approach shows a good correlation between video and field inspection for AC sections. In particular, patching and non-load crack indices provide good correlation. The MTC-PMS analysis showed strong linear relationships between video and field inspections. The analysis of crack indices from digitized images shows poor repeatability for each test loop. Using general linear model analysis, variable effects on crack indices were tested. The cost for development and operation of the system was estimated as well as cost for an enhanced prototype system. Discussions on various aspects of the developed system are provided. Finally, summary and conclusion are included as well as recommendations for future system development. PDF derivative scanned at 300 ppi (256 B&W, 256 Grayscale), using Capture Perfect 3.0.82, on a Canon DR-9080C. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
A Pavement Crack Image Analysis Approach Based on Automatic Image Dodging
  • Q Q Li
  • Q W Hu
Developments of Research on Road Pavement Surface Distress Image Recognition
  • R B Wang
  • C Wang
  • X M Chu
  • R.B. Wang
Wang, R.B., Wang, C., Chu, X.M.: Developments of Research on Road Pavement Surface Distress Image Recognition. Journal of Jilin University (Engineering and Technology Edition) 32, 91-97 (2002) (in Chinese)
Measurement of Surface Crack Width Based on Digital Image Processing
  • G R Ye
  • Q S Zhou
  • X W Lin
  • G.R. Ye
Ye, G.R., Zhou, Q.S., Lin, X.W.: Measurement of Surface Crack Width Based on Digital Image Processing. Journal of Highway and Transportation Research and Development 27, 75-78 (2010) (in Chinese)
Study on Pavement Crack Identification and Evaluation Technology Based on digital Image Processing. Chang’an University
  • J Zhang
Zhang, J.: Study on Pavement Crack Identification and Evaluation Technology Based on digital Image Processing. Chang'an University. Ph.D. Thesis (2004) (in Chinese)
Distress Identification Manual for the Long-Term Pavement Performance Project, SHRP-P-338
  • N F Hawks
  • T P Teng
  • W Y Bellinger
  • R B Rogers
  • C Baker
  • K L Brosseau
  • L C Humphrey
Hawks, N.F., Teng, T.P., Bellinger, W.Y., Rogers, R.B., Baker, C., Brosseau, K.L., Humphrey, L.C.: Distress Identification Manual for the Long-Term Pavement Performance Project, SHRP-P-338. National Research Council, Washington, D.C. (1993)
Proposal of Universal Cracking Indicator for Pavements
  • W D Paterson
Paterson, W.D.: Proposal of Universal Cracking Indicator for Pavements. Transportation Research Record 1455, TRB, National Research Council, Washington, D.C., pp.69-76 (1994)
Automated Pavement Distress Collection Techniques
T.R.B.E. NCHRP synthesis 334: Automated Pavement Distress Collection Techniques. Transportation Research Board of the National Academies, Washington, D.C. (2004)
Modem Pavement Management
  • R Haas
  • W R Hudson
  • J Zaniewski
  • R. Haas
Haas, R., Hudson, W.R., Zaniewski, J.: Modem Pavement Management. Krieger Publishing Company, Malabar (1994)
Development of a New Digital Pavement Image Processing Algorithm for Unified Crack Index Computation. University of Utah
  • Jitprasithsiri
Jitprasithsiri: Development of a New Digital Pavement Image Processing Algorithm for Unified Crack Index Computation. University of Utah. Ph.D. Thesis (1997)
Automated Pavement Imaging Grogram (APIP) for Pavement Cracks Classification and Quantification-A Photogrammetric Approach. The International Archives of the Photogrammetry
  • M Mustaffara
  • T C Lingb
  • O C Puanb
  • M. Mustaffara