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

Abstract

This paper summarizes the Global Road Damage Detection Challenge (GRDDC), a Big Data Cup organized as a part of the IEEE International Conference on Big Data’2020. The Big Data Cup challenges involve a released dataset and a well-defined problem with clear evaluation metrics. The challenges run on a data competition platform that maintains a leaderboard for the participants. In the presented case, the data constitute 26336 road images collected from India, Japan, and the Czech Republic to propose methods for automatically detecting road damages in these countries. In total, 121 teams from several countries registered for this competition. The submitted solutions were evaluated using two datasets test1 and test2, comprising 2,631 and 2,664 images. This paper encapsulates the top 12 solutions proposed by these teams. The best performing model utilizes YOLO-based ensemble learning to yield an F1 score of 0.67 on test1 and 0.66 on test2. The paper concludes with a review of the facets that worked well for the presented challenge and those that could be improved in future challenges.

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.

... Various studies [10][11][12][13][14][15] that take advantage of the latest developments in deep learning and computer vision techniques have been conducted to improve the efficiency of road maintenance. Most of these studies have focused on road damage inspections. ...
... Recently, the accurate real-time detection of road damage has become possible due to the development of several object detection frameworks, such as Faster R-CNN [16], YOLO series [17][18][19], and SSD [20]. For example, Maeda et al. [12,13] developed road damage detection methods using SSD Inception V2 and SSD MobileNet. In addition, the dataset published by these authors, named RDD-2018, in which eight different defects of the Japanese road network were proposed, has gained wide attention from researchers in this field. ...
... Year [10] Image classification 2014 [21] Image classification 2016 [11] Image segmentation 2015 [22] Image segmentation 2021 [12] Object detection 2018 [23] Object detection 2022 [13] Object detection 2020 [24] Image segmentation 2022 ...
Article
Full-text available
Road markings are vital to the infrastructure of roads, conveying extensive guidance and information to drivers and autonomous vehicles. However, road markings will inevitably wear out over time and impact traffic safety. At the same time, the inspection and maintenance of road markings is an enormous burden on human and economic resources. Considering this, we propose a road marking inspection system using computer vision and deep learning techniques with the aid of street view images captured by a regular digital camera mounted on a vehicle. The damage ratio of road markings was measured according to both the undamaged region and region of road markings using semantic segmentation, inverse perspective mapping, and image thresholding approaches. Furthermore, a road marking damage detector that uses the YOLOv11x model was developed based on the damage ratio of road markings. Finally, the mean average precision achieves 73.5%, showing that the proposed system successfully automates the inspection process for road markings. In addition, we introduce the Road Marking Damage Detection Dataset (RMDDD), which has been made publicly available to facilitate further research in this area.
... Furthermore, it has become increasingly crucial to address resource optimization concerns, particularly regarding inference speed and memory usage, to enable real-time deployment of these models. Specifically, results from previous IEEE BigData cup challenges in road damage detection show that training large models or ensembling more models often leads to better accuracy [3]- [5], but at the same time suffer from inference speed and hardware requirements for deployment [6]. ...
... In the field of road damage detection, several state-of-theart solutions have been proposed to tackle the challenges of detecting and classifying roadway defects. Arya et al. [3]- [5] presented a comprehensive series of methods for global roadway damage detection, emphasizing the development of robust models for diverse road conditions. Pham et al. [1] explored the use of Detectron2's Faster R-CNN implementation, highlighting its effectiveness in detecting road damages with high precision. ...
... 4) A tiny YOLOv7 model: Ensembling models is a wellknown strategy for improving prediction accuracy in road damage detections proven by many works in the past [3], [5], as it leverages the strengths of multiple models to make more robust decisions. However, this approach typically comes with a trade-off in terms of increased inference time and computational cost. ...
Preprint
Full-text available
Maintaining roadway infrastructure is essential for ensuring a safe, efficient, and sustainable transportation system. However, manual data collection for detecting road damage is time-consuming, labor-intensive, and poses safety risks. Recent advancements in artificial intelligence, particularly deep learning, offer a promising solution for automating this process using road images. This paper presents a comprehensive workflow for road damage detection using deep learning models, focusing on optimizations for inference speed while preserving detection accuracy. Specifically, to accommodate hardware limitations, large images are cropped, and lightweight models are utilized. Additionally, an external pothole dataset is incorporated to enhance the detection of this underrepresented damage class. The proposed approach employs multiple model architectures, including a custom YOLOv7 model with Coordinate Attention layers and a Tiny YOLOv7 model, which are trained and combined to maximize detection performance. The models are further reparameterized to optimize inference efficiency. Experimental results demonstrate that the ensemble of the custom YOLOv7 model with three Coordinate Attention layers and the default Tiny YOLOv7 model achieves an F1 score of 0.7027 with an inference speed of 0.0547 seconds per image. The complete pipeline, including data preprocessing, model training, and inference scripts, is publicly available on the project's GitHub repository, enabling reproducibility and facilitating further research.
... Data cup challenges differ from the general case of publicly available data, where researchers may train their own models, as it ensures fairness by fixing the train-test data split and providing standardized evaluation frameworks, with a timeline. These challenges provide insights into the contemporary methods and approaches employed by researchers worldwide, representing the current status quo in the field [16,17,[21][22][23]. ...
... Further information about the CRDDC dataset and other details for tasks, contributors, winners etc. are provided in [24] and [25]. Details of the Global Road Damage Detection Challenge (GRDDC) organized in 2020, targeting approaches for India, Japan, and Czech Republic are provided in [22]. Here it may be noted that, multi-view learning and handling multi-country data present significant challenges, such as missing or noisy information in multi-view data and variations in road damage data across different countries. ...
... It may be noted that most of the datasets consider either the topdown view, focussing on the road surface [47][48][49][50], or the horizontaldirection capturing a wide view of the road, road objects and surroundings [13,22,51,52]. Some authors like Majidifard et al. [54] have considered a combination of images capturing horizontal as well as topdown view of the road. ...
Article
Monitoring road conditions is crucial for safe and efficient transportation infrastructure, but developing effective models for automatic road damage detection is challenging requiring large-scale annotated datasets. Cross-country collaboration provide access to diverse datasets and insights into factors affecting road damage detection models. This paper presents a review of winning strategies of the Crowdsensing-based Road Damage Detection Challenge (CRDDC) held in 2022 as a Big Data Cup, with 90+ teams from 20+ countries proposing solutions for six countries: India, Japan, the Czech Republic, Norway, the United States, and China. The best solution achieved an F1-score of 77 % for all six countries, which is 2.7 % better than the 2nd ranked solution. This study explores the impact of factors influencing dataset and model selection by CRDDC winners. The study’s insights can guide future research in making data-related choices and developing more effective road damage detection models accounting for the diverse road conditions across different countries.
... In the field of road damage detection, several state-of-theart solutions have been proposed to tackle the challenges of detecting and classifying roadway defects. Arya et al. [4]- [6] presented a comprehensive series of methods for global roadway damage detection, emphasizing the development of robust models for diverse road conditions. Pham et al. [2] explored the use of Detectron2's Faster R-CNN implementation, highlighting its effectiveness in detecting road damages with high precision. ...
... 4) A tiny YOLOv7 model: Ensembling models is a wellknown strategy for improving prediction accuracy in road damage detections proven by many works in the past [4], [6], as it leverages the strengths of multiple models to make more robust decisions. However, this approach typically comes with a trade-off in terms of increased inference time and computational cost. ...
Conference Paper
Maintaining roadway infrastructure is essential for ensuring a safe, efficient, a nd sustainable transportation system. However, manual data collection for detecting road damage is time-consuming, labor-intensive, and poses safety risks. Recent advancements in artificial intelligence, particularly deep learning, offer a promising solution for automating this process using road images. This paper presents a comprehensive workflow for road damage detection using deep learning models, focusing on optimizations for inference speed while preserving detection accuracy. Specifically, to accommodate hardware limitations, large images are cropped, and lightweight models are utilized. Additionally, an external pothole dataset is incorporated to enhance the detection of this underrepresented damage class. The proposed approach employs multiple model architectures, including a custom YOLOv7 model with Coordinate Attention layers and a Tiny YOLOv7 model, which are trained and combined to maximize detection performance. The models are further reparameterized to optimize inference efficiency. Experimental results demonstrate that the ensemble of the custom YOLOv7 model with three Coordinate Attention layers and the default Tiny YOLOv7 model achieves an F1 score of 0.7027 with an inference speed of 0.0547 seconds per image. The complete pipeline, including data preprocessing, model training, and inference scripts, is publicly available on the project’s GitHub repository, enabling reproducibility and facilitating further research.
... The RDD2020 dataset was utilized for organizing the Global Road Damage Detection Challenge (GRDDC'2020) (Arya, Maeda, Ghosh, Toshniwal, Omata, et al., 2020). The challenge invited researchers across the globe to propose a single model for monitoring road conditions in the three based on RDD2022, underscoring its continued relevance and pivotal role in current research and development endeavors. ...
... Further, the analysis conducted by Arya, Maeda, Ghosh, Toshniwal, Mraz, et al. (2021) indicated that adding data from other countries helps improve the generalizability of models trained for detecting road damage in any country. This analysis and the tremendous success of the GRDDC'2020 (Arya, Maeda, Ghosh, Toshniwal, Omata, et al., 2020) are the motivation behind introducing the current dataset RDD2022. It aims to solve road damage detection for a more extensive set of countries, targeting solutions for India, Japan, the Czech Republic, Norway, China, and the United States. ...
Article
Full-text available
The data article describes the Road Damage Dataset, RDD2022, encompassing of 47,420 road images from majorly six countries, Japan, India, the Czech Republic, Norway, the United States, and China. The dataset incorporates over 55,000 instances of road damage, specifically longitudinal cracks, transverse cracks, alligator cracks, and potholes. Designed to facilitate the development of deep learning methodologies for automated road damage detection and classification, RDD2022 was unveiled as part of the Crowd sensing‐based Road Damage Detection Challenge (CRDDC'2022), with a major contribution from the challenge winners. This challenge garnered global participation, urging researchers to propose solutions for automatic road damage detection in multiple countries. A noteworthy outcome of CRDDC'2022 was the emergence of a top‐performing model achieving a remarkable F1 Score of 76.9% for road damage detection in all six countries using RDD2022. This success underscores the dataset's practical applicability for municipalities and road agencies, enabling low‐cost, automatic monitoring of road conditions. Beyond its immediate utility, RDD2022 stands as a valuable benchmark for researchers in computer vision, geoscience, and machine learning, offering a rich resource for algorithmic evaluation in diverse image‐based applications, including classification and object detection. The latest big data cup, Optimized Road Damage Detection Challenge (ORDDC'2024), is also based on RDD2022, underscoring its continued relevance and pivotal role in current research and development endeavors.
... The dataset utilized by the proponents was a combined self-generated image dataset captured in the Philippines and an image dataset from Road Damage Dataset, RDD2022 which has been released as a part of the Crowd sensing-based Road Damage Detection Challenge from Asian countries specifically Japan and India [5]. Japan and India were chosen as these two countries were the only Asian countries that participated in the mentioned event with significant diversity. ...
... In 2012, AlexNet's success at the ImageNet Challenge marked the beginning of the deep learning era [11]. The rise of deep learning has revolutionized the field of target detection [12][13][14]. Deep learning's powerful data processing and pattern recognition capabilities, which automate road damage detection, greatly reduce labor costs, and enable real-time detection and instant updates of road conditions, have led to its increasing use in road damage detection [15][16][17]. ...
Article
Full-text available
To address challenges such as variations in lighting, weather, and the size and shape of cracks and potholes, we propose an enhanced end-to-end regression algorithm for autonomous road damage detection. This method balances computational efficiency and accuracy by incorporating feature extraction structures to improve performance in scenarios involving multiple damage types, shadows, and fine-grained feature variations. The proposed model integrates a down-sampling structure for dimensionality reduction and feature extraction, an inverted residual mobile block for feature fusion, and an attention mechanism with multi-scale features for multi-scale detail extraction. Additionally, the integration of a Decoupled Head structure enhances bounding box localization. Experimental results show that the proposed method outperforms YOLOv5s (You Only Look Once version 5 small), achieving a 2.9% improvement in the F1 score and a 4% improvement in the mean average precision. Further validation through visualization experiments in seven challenging road scenarios, including varying lighting and environmental conditions, highlights the model’s superior detection accuracy, completeness, and robustness.
... Road maintenance plays an important role in the socio-economic development of a country. To avoid future damage, better construction methods and the use of highquality materials should also be considered (Arya D. M., 2022). ...
Article
Full-text available
The development of road infrastructure in various countries is growing rapidly in line with the increasing need for more efficient transportation and better road access to various regions. Suppose in a country the road infrastructure is damaged. In that case, it will result in limited access to more efficient transportation, hinder the mobility of road and goods users, and potentially slow down economic growth. This study aims to determine the level of satisfaction of road users with the condition of the pavement on Jl. Pejuang-Sindangkasih, and determine the level of existing damage. This research is located on Jl. Pejuang-Sindangkasih, which is located in Majalengka District, Majalengka Regency, West Java. The data collection technique used is a questionnaire, which is intended to collect data on the level of damage felt, the impact of damage on comfort and safety, and road users' expectations for road repairs. Overall, this data provides a clear picture of the profile of road users on Jl. Pejuang-Sindangkasih and how they see the condition of the road. This information can be an important basis for road repair and maintenance to improve comfort and safety for all road users. Some respondents also emphasized the importance of immediate repairs to road damage to reduce the risk of accidents and vehicle damage. In addition, respondents from younger age groups tend to be more critical of road conditions and show a high awareness of the importance of good road infrastructure. Road damage is very dangerous for road users, especially for motorcycle users, and urgent repairs are needed. Overall, this information provides important information about the planning and implementation of road repairs, with a special emphasis on the most important elements to improve the safety and comfort of road users.
... The dataset used in this study is from the open-source RDD2022 dataset released by CRDDC [18]. This dataset includes road images from multiple countries, annotated with various road defects. ...
Article
Full-text available
Road defect detection is crucial for enhancing traffic safety, optimizing urban management efficiency, and promoting sustainable urban development. Traditional manual detection methods are inefficient and costly, and most deep learning-based road defect detection models lack superior feature extraction capabilities in complex environments. To address this challenge, this paper proposes an innovative detection framework based on an improved YOLOv5 network. To reduce the processing required for feature extraction and improve detection speed, this study introduces the C3ghost module in both the backbone and neck networks. Furthermore, to enhance the model’s feature extraction capability, this research incorporates the Explicit Visual Center (EVC) module to optimize the feature pyramid layer, thereby improving the model’s detection performance. Additionally, the adaptive feature augmentation dynamic detection head (DyHead) module is introduced to enhance the model’s ability to capture target features at different scales. To validate the performance of the proposed algorithm, it was tested using the RDD2022 dataset. The experimental results demonstrate that the enhanced algorithm achieved an mAP@0.5 of 81.6%, with a precision of 83.1% and a recall of 79.8%. These results indicate improvements of 2.9%, 3.7%, and 7.2% in comparison to the original YOLOv5s algorithm. Moreover, there was a 4.4% decrease in FLOPs. This further illustrates the effectiveness and superiority of the proposed algorithm, providing valuable insights for advancing real-time road defect detection methods.
... The best 12 answers that these teams came up with are summarized in this publication. YOLO-based ensemble learning is employed by the top-performing model, which yields an F1 score of 0.67 on test 1 and o.66 on test [30]. ...
... Guo et al. [48] introduce MN-YOLOv5, incorporating MobileNetV3 [49] and coordinate attention [50] for mobile deployment. In the Crowdsensing-based Road Damage Detection Challenge (CRDDC'2022 [51][52][53][54][55]), team Shi Yu_Sea View fuse YOLO and Faster R-CNN algorithms to enhance global information utilization and achieve top results. ...
Article
Full-text available
As an essential object detection application, road damage detection aims to identify and mark road damage. Timely maintenance of detected damage can improve road safety. However, the proportions of damage area of the image is very diffident for the variety of the road damage textures and shapes. Additionally it is a challenge to localize the road damage accurately for the blurring of the damaged regions caused by the external environmental factors. In this study, we propose a Road Damage Detector with a Local Sensing Feature Network (LSF-RDD), which constructs a Local Sensing Feature Network (LSF-Net) as a neck to fuse multi-scale features extracted from the backbone network and can focus on the location of the damaged area. First, the CSP-Darknet53 backbone network extracts the feature maps of three scales layer-by-layer from the input images. Second, these three feature maps are input into LSF-Net for multi-scale feature fusion to generate three local feature representations. LSF-Net comprises four interconnected blocks, enabling top-down and bottom-up feature fusion. Feature maps from the backbone perform multi-scale feature fusion through connections between different blocks. Finally, three local feature representations are sent into the detection head for detection. Experiments show that LSF-RDD performs well on the adopted datasets, especially on the China_motorbike dataset of RDD2022, with mAP@0.5 reaching 94.4%.
... The evolution of road damage detection methodologies has transitioned from basic manual inspections to advanced automated and image processing techniques [16]. Initially, manual inspections constituted the primary approach, relying on the subjective assessment of trained personnel. ...
Article
Full-text available
In addressing the challenges of enhancing road damage detection efficiency and accuracy, this paper introduces an optimized YOLOv8 model suitable for embedded systems. The model significantly enhances precision, recall, and mean Average Precision (mAP), achieving 65.7% mAP on the RDD2022 dataset, thereby surpassing models such as Faster R-CNN and SSD. This advancement is attributed to the integration of a Deformable Attention Transformer, a GSConv-powered slim-neck module, and the MPDIoU loss function. These innovations not only contribute to the model's high performance but also set a new benchmark in road damage detection technology, thereby paving the way for future enhancements in the field.
... To verify the robustness and generalizability of our model, we carried out Experiment 3 on the Indian dataset 35 and Experiment 4 on the GRDDC (Global Road Damage Detection Challenge) dataset 45 . The outcomes of these experiments indicate that our enhanced model demonstrates superior accuracy and increased speed in detecting road defects compared to different models. ...
Article
Full-text available
Road defect detection is critical step for road maintenance periodic inspection. Current methodologies exhibit drawbacks such as low detection accuracy, slow detection speed, and the inability to support edge deployment and real-time detection. To solve this issue, we introduce an improved YOLOv8 road defect detection model. Firstly, we designed the EMA Faster Block structure using partial convolution to replace the Bottleneck structure in the YOLOv8 C2f module, and the enhanced C2f module was labeled as C2f-Faster-EMA. Secondly, we improved the model speed by introducing SimSPPF instead of SPPF. Finally, for the head, Detect-Dyhead, chosen to replace the original head, significantly improves the representation ability of heads without introducing any GFLOPs. Experimental results on the road defect detection dataset show that the improved model in this paper outperforms the original YOLOv8, with a 5.8% increase in average accuracy (mAP@0.5), and notable reductions of 22.33% in model size, 23.03% in parameter size, and 21.68% in computational complexity.
... Dataset. In this experiment, we use RDD2022 [51], [52], [53], a public data set for road surface defect study, which data was collected from six countries: China, Japan, Czech, India, Norway, and the United States. We use six data sources for this dataset, which correspond to six countries: China MotorBike, Czech, India, Japan, Norway, and the United States. ...
Preprint
Full-text available
Roads are an essential mode of transportation, and maintaining them is critical to economic growth and citizen well-being. With the continued advancement of AI, road surface inspection based on camera images has recently been extensively researched and can be performed automatically. However, because almost all of the deep learning methods for detecting road surface defects were optimized for a specific dataset, they are difficult to apply to a new, previously unseen dataset. Furthermore, there is a lack of research on training an efficient model using multiple data sources. In this paper, we propose a method for classifying road surface defects using camera images. In our method, we propose a scheme for dealing with the invariance of multiple data sources while training a model on multiple data sources. Furthermore, we present a domain generalization training algorithm for developing a generalized model that can work with new, completely unseen data sources without requiring model updates. We validate our method using an experiment with six data sources corresponding to six countries from the RDD2022 dataset. The results show that our method can efficiently classify road surface defects on previously unseen data.
... In this article, we reclassify and organize the RDD2022 [27] used in Crowdsensing-based Road Damage Detection Challenge [27,[50][51][52]. Based on the shooting perspective, we change the dataset from its original classification based on countries to a classification based on different photographic perspectives. ...
Article
Full-text available
Road damage detection using computer vision and deep learning to automatically identify all kinds of road damage is an efficient application in object detection, which can significantly improve the efficiency of road maintenance planning and repair work and ensure road safety. However, due to the complexity of target recognition, the existing road damage detection models usually carry a large number of parameters and a large amount of computation, resulting in a slow inference speed, which limits the actual deployment of the model on the equipment with limited computing resources to a certain extent. In this study, we propose a road damage detector named LMFE-RDD for balancing speed and accuracy, which constructs a Lightweight Multi-Feature Extraction Network (LMFE-Net) as the backbone network and an Efficient Semantic Fusion Network (ESF-Net) for multi-scale feature fusion. First, as the backbone feature extraction network, LMFE-Net inputs road damage images to obtain three different scale feature maps. Second, ESF-Net fuses these three feature graphs and outputs three fusion features. Finally, the detection head is sent for target identification and positioning, and the final result is obtained. In addition, we use WDB loss, a multi-task loss function with a non-monotonic dynamic focusing mechanism, to pay more attention to bounding box regression losses. The experimental results show that the proposed LMFE-RDD model has competitive accuracy while ensuring speed. In the Multi-Perspective Road Damage Dataset, combining the data from all perspectives, LMFE-RDD achieves the detection speed of 51.0 FPS and 64.2% mAP@0.5, but the parameters are only 13.5 M.
... In our dataset, like in many others, a pre-defined 0.5 IoU threshold is set to classify whether a prediction is deemed a true positive or a false positive. [17][18][19][20][21][22]. ...
Article
Full-text available
Improving urban mobility, especially pedestrian mobility, is a current challenge in virtually every city worldwide. To calculate the least-cost paths and safer, more efficient routes, it is necessary to understand the geometry of streets and their various elements accurately. In this study, we propose a semi-automatic methodology to assess the capacity of urban spaces to enable adequate pedestrian mobility. We employ various data sources, but primarily point clouds obtained through a mobile laser scanner (MLS), which provide a wealth of highly detailed information about the geometry of street elements. Our method allows us to characterize preferred pedestrian-traffic zones by segmenting crosswalks, delineating sidewalks, and identifying obstacles and impediments to walking in urban routes. Subsequently, we generate different displacement cost surfaces and identify the least-cost origin–destination paths. All these factors enable a detailed pedestrian mobility analysis, yielding results on a raster with a ground sampling distance (GSD) of 10 cm/pix. The method is validated through its application in a case study analyzing pedestrian mobility around an educational center in a purely urban area of A Coruña (Galicia, Spain). The segmentation model successfully identified all pedestrian crossings in the study area without false positives. Additionally, obstacle segmentation effectively identified urban elements and parked vehicles, providing crucial information to generate precise friction surfaces reflecting real environmental conditions. Furthermore, the generation of cumulative displacement cost surfaces allowed for identifying optimal routes for pedestrian movement, considering the presence of obstacles and the availability of traversable spaces. These surfaces provided a detailed representation of pedestrian mobility, highlighting significant variations in travel times, especially in areas with high obstacle density, where differences of up to 15% were observed. These results underscore the importance of considering obstacles’ existence and location when planning pedestrian routes, which can significantly influence travel times and route selection. We consider the capability to generate accurate cumulative cost surfaces to be a significant advantage, as it enables urban planners and local authorities to make informed decisions regarding the improvement of pedestrian infrastructure.
... (3) As depicted in Fig. 9, the crack dataset 3 from GRDDC'2020 comprises 26,336 road images collected from India, Japan, and the Czech Republic. This dataset is utilized to develop methods for automatically detecting road damages in these respective countries [47]. It is important to note that the dataset does not exclusively consist of crack targets. ...
Article
Full-text available
Rapid real-time detection of crack images helps prevent the emergence of more significant potential hazards. However, mature and sophisticated convolutional neural networks are more concerned with images of general everyday objects. These neural networks do not meet the real-time requirements for concrete defect detection for cracks with complex morphology and varying scales. This manuscript proposes a lightweight improvement strategy, which consists mainly of malleable efficient channel pruning, a more scaled wide-area receptive field (MSWR), and multi-channel fusion of spatial attention, referred to as MMM strategies. Firstly, the channel pruning count can intuitively make the general convolutional neural network more lightweight. Secondly, the wider receptive field can fuse multi-scale feature maps and recognize cracks of various scales. Finally, the multi-channel fusion of spatial attention enhances detection performance efficiently, ensuring real-time capability at minimal cost. The experimental results show that the lightweight network improved by the MMM strategy sacrifices no more than 8% in the detection accuracy of defects. In some cases, the detection accuracy is even improved, while the detection speed has a significant advantage. This lightweight strategy improves defect detection and has higher real-time adaptability than mainstream convolutional neural networks. The codes are available at https://github.com/mmm587/MMM.
... Totally 22 categories of objects and damage instances at the pixel level are annotated, facilitating the fine-grained segmentation of road damage. The Road Damage Dataset (RDD) series datasets [15][16][17][18] , which was recently updated from 2018 to 2022, uses smartphones installed on windshields to capture wide view road images and annotates 19 . Despite the great progress made by these studies on the application of deep learning algorithms for the detection of road pavement damages, they are usually associated with high acquisition costs, varying image resolutions, and restricted image views, which imped the practical application of the associated models. ...
Article
Full-text available
Road damage is a great threat to the service life and safety of roads, and the early detection of pavement damage can facilitate maintenance and repair. Street view images serve as a new solution for the monitoring of pavement damage due to their wide coverage and regular updates. In this study, a road pavement damage dataset, the Street View Image Dataset for Automated Road Damage Detection (SVRDD), was developed using 8000 street view images acquired from Baidu Maps. Based on these images, over 20,000 damage instances were visually recognized and annotated. These instances were distributed in five administrative districts of Beijing City. Ten well-established object detection algorithms were trained and assessed using the SVRDD dataset. The results have demonstrated the performances of these algorithms in the detection of pavement damages. To the best of our knowledge, SVRDD is the first public dataset based on street view images for pavement damages detection. It can provide reliable data support for future development of deep learning algorithms based on street view images.
... For validating the performance of the algorithm presented in this paper, we compare RDD-YOLO with high-accuracy models such as YOLOv5x, YOLOv7x, and YOLOv8x proposed in recent years. Additionally, we introduce p-YOLOv5x for comparison, a model that uses pre-trained weights from the winning solution in the Global Road Damage Detection Challenge (GRDDC'2020) [32] proposed by Hegde V et al. [33]. As illustrated in Table 2, the comparison reveals that higher versions of YOLO models have a smaller parameter count compared to lower versions, and the YOLOv8x model outperforms lower versions in terms of performance. ...
Article
Full-text available
The detection of road damage is highly important for traffic safety and road maintenance. Conventional detection approaches frequently require significant time and expenditure, the accuracy of detection cannot be guaranteed, and they are prone to misdetection or omission problems. Therefore, this paper introduces an enhanced version of the You Only Look Once version 8 (YOLOv8) road damage detection algorithm called RDD-YOLO. First, the simple attention mechanism (SimAM) is integrated into the backbone, which successfully improves the model’s focus on crucial details within the input image, enabling the model to capture features of road damage more accurately, thus enhancing the model’s precision. Second, the neck structure is optimized by replacing traditional convolution modules with GhostConv. This reduces redundant information, lowers the number of parameters, and decreases computational complexity while maintaining the model’s excellent performance in damage recognition. Last, the upsampling algorithm in the neck is improved by replacing the nearest interpolation with more accurate bilinear interpolation. This enhances the model’s capacity to maintain visual details, providing clearer and more accurate outputs for road damage detection tasks. Experimental findings on the RDD2022 dataset show that the proposed RDD-YOLO model achieves an mAP50 and mAP50-95 of 62.5% and 36.4% on the validation set, respectively. Compared to baseline, this represents an improvement of 2.5% and 5.2%. The F1 score on the test set reaches 69.6%, a 2.8% improvement over the baseline. The proposed method can accurately locate and detect road damage, save labor and material resources, and offer guidance for the assessment and upkeep of road damage.
... In order to verify whether the algorithm in this paper has advantages on other data sets, experiments were conducted on the public data set RDD2022 [19] and the public data set global road damage detection challenge (GRDDC) [25]. To ensure the reliability of the experiments, they were all tested on the same equipment and under the same parameters. ...
Article
Full-text available
The detection of pavement diseases is an important and basic link in the road maintenance process. Many methods based on deep learning have been applied. However, these methods are not accurate enough and cannot accurately identify defects in complex background with shadow occlusion and uneven lighting brightness. In order to overcome the shortcomings of previous detection methods, a complex background defect detection algorithm based on improved YOLOv7 is proposed. First, the K-means++ clustering algorithm is used for initial anchor box setting to obtain better anchor box parameters; then, the group spatial pyramid pooling module SPPCSPC_G is introduced to replace the original SPPCSPC module to improve the fusion speed of image features and thereby improve the detection accuracy; Finally, the GELU activation function is used as the activation function of the REPConv convolution module in the YOLOv7 model, which effectively reduces model overfitting and thereby improves model detection accuracy. The test results show that the average accuracy of the improved detection algorithm for disease detection increased from 65.4% to 72.3%, an increase of 6.9%, the amount of calculation and parameters decreased by 4% and 14.9% respectively, and the FPS reached 80, an increase of 17%, and no pavement defects are missed or wrongly detected. It is more suitable for real-time detection of defects in complex background. It can be seen that the improved YOLOv7 has better detection effect on complex background defects.
... Image processing has been applied to many fields such as forestry to evaluate the impacts of policies addressing deforestation (MathWorks Inc., 2021), transportation infrastructure for road damage detection (Maeda et al., 2018;Arya et al., 2020aArya et al., , 2020bArya et al., , 2021, and dermatology to determine the severity of skin cancer (Kinyanjui et al., 2019) and skin lesions (Mirikharaji et al., 2021). Zou et al. (2022) applied deep learning using the You Only Look Once version 4 (YOLOv4) algorithm to detect defects in structures after an earthquake disaster. ...
Article
Full-text available
Pavement management has traditionally relied on human-based decisions. In many countries, however, the pavement stock has recently increased, while the number of management experts has declined, posing the challenge of how to efficiently manage the larger stock with fewer resources. Compared to efficient computer-based techniques, human-based methods are more prone to errors that compromise analysis and decisions. This research built a robust probabilistic pavement management model with a safety metric output using inputs from image processing tested against the judgment of experts. The developed model optimized road pavement safety. The study explored image processing techniques considering the trade-off between processing cost and output accuracy, with annotation precision and intersection over union (IoU) set objectively. The empirical applicability of the model is shown for selected roads in Japan.
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.
Conference Paper
Efficient road damage detection is key for timely maintenance and decreasing long-term costs, especially for large-scale road networks. While existing models achieve high accuracy, they often overlook resource optimization, making them impractical for widespread deployment. In this study, we propose an optimized approach using the YOLOv10 model, designed to balance detection accuracy and inference speed, enabling scalable road damage detection across diverse regions. Key to our success were several optimization techniques, including strategic data sampling from a large, diverse dataset of 47,420 images across six countries, automated hyperparameter tuning for 10,000 epochs, and advanced data augmentation methods such as Bounding-Box-Safe Random Crop and Optimized Test-Time Augmentation. These strategies enhanced the model’s robustness and generalization across varying road damages. Our model was developed in response to the Optimized Road Damage Detection Challenge (ORDDC) 2024, where we attained an F1 score of 0.7073 and an inference speed of 0.2886, securing 5th place.
Article
Effective and efficient detection of pavement distress is very important for the normal use and maintenance of roads. To achieve this goal, a new road damage detection method based on YOLOv8 is proposed in this article. Firstly, omni-dimensional dynamic convolution (ODConv) block is employed to better grasp the complex and diverse features of damage objects by making dynamic adjustment according to the features of input images. Secondly, to extract the global and local feature information simultaneously to better improve the feature extraction ability of the model, BoTNet is added to the end of the backbone, which can combine the advantages of convolutional neural network (CNN) and Transformer. Finally, the coordinate attention mechanism (CA) is incorporated into the Neck section to make more accurate speculations and enhance detection accuracy further which can effectively mitigate irrelevant feature interference. The new proposed model is named OBC-YOLOv8 and the experimental results on the RDD2022-China dataset demonstrate its superiority compared with baselines, with 1.8% and 1.6% increases in mean average precision 50 (mAP@0.5) and F1-score, respectively.
Article
Road damage seriously affects the comfort and safety of drivers. The detection of road damage is of great importance not only for transportation safety, but also in terms of cost. The detection of road damage is critical for enabling early intervention and repair. In this study, the road damage detection performance of the YOLO (You Only Look Once) v8 algorithm has been evaluated using datasets obtained from different geographies, including Czechia -Türkiye, India-Türkiye, USA-Türkiye, and Japan-Türkiye. The findings revealed both the capabilities of the algorithm in damage detection and the challenges it faced in distinguishing certain types of damage. For the creation of the Türkiye dataset, images of roads in the province of Hatay were recorded. These images were labeled using Microsoft's VoTT application. Comparisons and evaluations have been made among the developed models. Among these models, the Japan-Türkiye model yielded the best results with a 0.55 mAP and 0.54 F1 score. The results of the models indicated that the appearance of damage varies according to the geographical location and the quality of road data. The importance of training on local images and indistinct types of damage has been observed.
Chapter
Road maintenance technology is crucial for safe driving and accident prevention. Traditional methods using sensor-equipped trucks are costly for many local governments. Affordable devices like smartphones can scan road surfaces. Machine learning (ML) and deep learning (DL) models can effectively detect road damages. The authors used various versions of the “You Only Look Once” (YOLO) algorithm (YOLOv3, YOLOv5, YOLOv6, YOLOv7) with the Road Damage Detection 2020 (RDD 2020) dataset. Data augmentation through transformations and generative adversarial network (GAN) enhanced the dataset. DL models were trained using three methods: from scratch, transfer learning, and hyperparameter tuning. YOLOv6, trained with GAN-based augmentation and hyperparameter tuning, achieved the best results: 0.80 Precision, 0.85 Recall, 0.676 mAP@0.5, and 0.438 mAP@0.5:0.95. Dynamic range quantization reduced the model size by 75% without compromising accuracy. This study highlights YOLOv6 with GAN-based augmentation and hyperparameter tuning as a cost-effective road maintenance solution.
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
The balance between detection accuracy and real-time performance in road surface damage detection models has not been achieved. To address the characteristics of complex backgrounds, significant variations in target shapes and scales, a large number of small targets, and high real-time requirements in road surface damage images, we propose the FG_YOLO object detection algorithm based on YOLOv5s. To effectively reduce model parameters and improve detection speed, we designed the FasterBottle Neck module based on Partial Convolution and Separable Convolution to replace the main computational modules in YOLOv5s. This approach reduces model parameters while effectively enhancing detection accuracy. Additionally, we incorporated a Global Attention Mechanism during the feature extraction stage to significantly improve the model’s ability to extract features for targets with varying shapes and small targets in complex backgrounds, thereby enhancing the detection capability for small targets. To address the imbalance between positive and negative labels during the training phase, we replaced the loss function to accelerate model convergence. Validation on the public dataset GRDDC2020 shows that the algorithm achieves an average precision of 55.8%, a detection speed of 115 frames per second, and a model parameter size of 6.08 M. Compared to YOLOv5s, the average precision increased by 4.7%, the detection speed increased by 3 frames per second, and the model parameters decreased by 13.4%, meeting the requirements for both detection accuracy and speed in road surface damage detection. The improved model’s effectiveness is also demonstrated on the UAV-PDD2023 dataset.
Article
Intelligent detection of pavement damage is crucial to road maintenance. Timely identification of cracks and potholes helps prolong the road service life. Current detection models fail to balance accuracy and speed. In this study, we propose a fast damage detection algorithm named FPDDN to achieve real-time and high-accuracy pavement damage detection. FPDDN integrates the deformable transformer, D2f block, and SFB module to predict pavement damage of different sizes in multiple branches. The deformable transformer allows the FPDDN to exhibit adaptability to geometric variations in road defects, thereby improving the detection accuracy of irregular defects such as cracks. D2f block is mainly used to lightweight the network and increase the inference speed. The SFB module can significantly decrease the loss of information during downsampling of small-sized objects. This integration enhances the model’s ability to extract global damage features, reduces the loss of information on small-scale defects, and improves the synergy between deep and shallow feature layers. The model’s performance was evaluated using the RDD2022 dataset, focusing on inference speed and detection accuracy. When compared to state-of-the-art models such as YOLO v8, FPDDN has a parameter count that is only one-fifth of that of YOLO v8x, yet it surpasses YOLO v8x in detection accuracy. The FPDDN achieved an F1 score of 0.601 and a mAP50 of 0.610 on the RDD2022 dataset, outperforming the compared models. Additionally, the algorithm achieved a balance between accuracy and speed with an inference speed of 1.8ms for pavement damage detection.
Article
Full-text available
Road damage detection is an crucial task to ensure road safety. To tackle the issues of poor performance on multi-scale pavement distresses and high costs in detection task, this paper presents an improved lightweight road damage detection algorithm based on YOLOv8n, named YOLOv8-PD (pavement distress). Firstly, a BOT module that can extract global information of road damage images is proposed to adapt to the large-span features of crack objects. Secondly, the introduction of the large separable kernel attention (LKSA) mechanism enhances the detection accuracy of the algorithm. Then, a C2fGhost block is constructed in the neck network to strengthen the feature extraction of complex road damages while reducing the computational load. Furthermore, we introduced lightweight shared convolution detection head (LSCD-Head) to improve feature expressiveness and reduce the number of parameters. Finally, extensive experiments on the RDD2022 dataset yield a model with parametric and computational quantities of 2.3M and 6.1 GFLOPs, which are only 74.1% and 74.3% of the baseline, and the mAP reaches an improvement of 1.4 percentage points from the baseline. In addition, experimental results on the RoadDamage dataset show that the mAP increased by 4.2% and this algorithm has good robustness. This method can provide a reference for the automatic detection method of pavement distress.
Article
Road damage presents a significant risk to traffic safety, including pavement distress and disaster-induced damage. Thanks to their high efficiency, computer vision-based methods for pavement distress detection have been widely developed. In disaster scenarios, the automatic extraction of road damage information from extensive social media images plays a critical role in rescue efforts. However, few existing studies have focused on detecting object-level disaster-induced road damage. To fill the gap, this paper presents a Social media image dataset of Object detection for Disaster-induced Road damage (SODR), including 1,552 images and two categories (i.e., collapses and blockages). Additionally, this paper proposes an ensemble learning approach with attention mechanisms based on YOLOv5 (You Only Look Once) network. Initially, attention modules are employed to create two distinct detectors for ensemble learning. Subsequently, one standard YOLOv5 and two variant networks are trained with consistent settings, and test time augmentation is applied during the inference phase. The proposed method has been implemented across five scales of YOLOv5, offering alternatives for balancing accuracy and computational cost. To demonstrate the validity, comprehensive experiments were conducted on two datasets. Compared with some mainstream detectors and ensemble learning methods, our approach achieved competitive results with a fewer number of parameters and a simpler training and testing process. The SODR dataset and source code are available at ( https://github.com/nonondayo/yolov5_SODRv1 ).
Article
Road damage detection (RDD) based on front-view images of roads is more in line with practical application scenarios and is suitable for automatic road damage detection systems. The road damage objects in the front-view images have the characteristics of complex background, multi-scale and large aspect ratio, which greatly increase the difficulty of detection. We propose an anchor-free road damage detection model YOLOX-RDD for front-view images. YOLOX is used as the basic network and three optimization strategies are implemented according to the characteristics of road damage objects. The refined switchable atrous convolution (RSAC) is used to adaptively adjust the receptive field according to the size of the object, which can satisfy the requirements of the detection of the damages of multi-scale and large aspect ratio. For unobvious road damage detection in complex background, four feature enhancement attention (FEA) modules are added to the network to extract more salient information and enhance the fusion effect. Two-level adaptive spatial feature fusion (ASFF) is performed by fusing dark2 with the three output feature maps of neck respectively, and the optimal fusion weights are learned through training to further improve the detection capability of multi-scale objects. The experiments on CNRDD, RDD2020 and USRDD datasets demonstrate the effectiveness and high generalization of our method. Compared with the baseline model, the mAP @0.5 can be improved by up to 2.78%, and F1{F}1 -Score can be improved by up to 2.55%. The FPS can reach up to 90, achieving a balance between detection accuracy and speed.
Article
Ensuring traffic safety is crucial, which necessitates the detection and prevention of road surface defects. As a result, there has been a growing interest in the literature on the subject, leading to the development of various road surface defect detection methods. The methods for detecting road defects can be categorised in various ways depending on the input data types or training methodologies. The predominant approach involves image-based methods, which analyse pixel intensities and surface textures to identify defects. Despite popularity, image-based methods share the distinct limitation of vulnerability to weather and lighting changes. To address this issue, researchers have explored the use of additional sensors, such as laser scanners or LiDARs, providing explicit depth information to enable the detection of defects in terms of scale and volume. However, the exploration of data beyond images has not been sufficiently investigated. In this survey paper, we provide a comprehensive review of road surface defect detection studies, categorising them based on input data types and methodologies used. Additionally, we review recently proposed non-image-based methods and discuss several challenges and open problems associated with these techniques.
Preprint
Full-text available
Road damage detection is an crucial task to ensure road safety. To tackle the issues of poor performance on multi-scale cracks and high costs in road damage detection, this paper presents an improved lightweight road damage detection algorithm based on YOLOv8n, named YOLOv8-PD (Pavement Disease). Firstly, a BOT module that can extract global information of road damage images is proposed to adapt to the large-span features of crack objects. Secondly, the introduction of the Large Separable Kernel Attention (LKSA) mechanism enhances the detection accuracy of the algorithm. Then, a C2fGhost block is constructed in the neck network to strengthen the feature extraction of complex road diseases while reducing the computational load. Furthermore, we introduced Lightweight Shared Convolution Detection Head (LSCD-Head) to improve feature expressiveness and reduce the number of parameters. Finally, extensive experiments on the RDD2022 dataset yield a model with parametric and computational quantities of 2.3M and 6.1 GFLOPs, which are only 74.1% and 74.3% of the baseline, and the mAP reaches an improvement of 1.4 percentage points from the baseline. In addition, experimental results on the RoadDamage dataset show that the mAP increased by 4.2% and this algorithm has good robustness. This method can provide a reference for the automatic detection method of pavement cracks.
Article
Deep learning is widely used for road damage detection, but it requires extensive, diverse, and well‐labeled data. Centralized model training can be difficult due to large data transfers, storage needs, and computational resources. Data privacy concerns can also hinder data sharing among clients, leaving them to train models on their own data, leading to less robust models. Federated learning (FL) addresses these problems by training models without data sharing, only exchanging model parameters between clients and the server. This study deploys FL along with YOLOv5l to generate models for single‐ and multi‐country applications. These models gave 21%–25% lesser mean average precision (mAP) than centralized models but outperformed local client models by 1.33%–163% on the global test data.
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.
Article
Full-text available
Machine learning can produce promising results when sufficient training data are available; however, infrastructure inspections typically do not provide sufficient training data for road damage. Given the differences in the environment, the type of road damage and the degree of its progress can vary from structure to structure. The use of generative models, such as a generative adversarial network (GAN) or a variational autoencoder, makes it possible to generate a pseudoimage that cannot be distinguished from a real one. Combining a progressive growing GAN along with Poisson blending artificially generates road damage images that can be used as new training data to improve the accuracy of road damage detection. The addition of a synthesized road damage image to the training data improves the F ‐measure by 5% and 2% when the number of original images is small and relatively large, respectively. All of the results and the new Road Damage Dataset 2019 are publicly available (https://github.com/sekilab/RoadDamageDetector).
Conference Paper
Full-text available
Cyber attacks cause great damage to our national security, ranging from individual internet user to biggest governmental/industrial organizations, such as Equifax (Data Breach 145.5 Million Accounts, reported in July 2017) or Uber (Data Breach 57 Million Records, reported in November 2017). The cyber assault has significantly increased in breadth and depth. This paper introduces CVExplorer, a novel interactive system for visualizing cybersecurity threats reported in the National Vulnerability Database. The proposed system aims to work as a reporting and alerting tool that can help enhance the security against cyber attacks can potentially reduce network vulnerabilities. The CVExplorer system containing multiple linked views allows users to visualize the relationships of various dimensions in the large number of vulnerability reports, such as types and levels of vulnerability, vendors, and products. The CVExplorer provides an intuitive interface and supports a range of interactive features, such as filtering and ordering by vulnerability severity ratings, allowing users to narrow down topics of interest quickly. To demonstrate the effectiveness of the proposed system, we demonstrate the CVExplorer on two case studies of Common Vulnerabilities and Exposures retrieved from the National Vulnerability Database.
Article
Full-text available
Research on damage detection of road surfaces using image processing techniques has been actively conducted. This study makes three contributions to address road damage detection issues. First, to the best of our knowledge, for the first time, a large‐scale road damage data set is prepared, comprising 9,053 road damage images captured using a smartphone installed on a car, with 15,435 instances of road surface damage included in these road images. Next, we used state‐of‐the‐art object detection methods using convolutional neural networks to train the damage detection model with our data set, and compared the accuracy and runtime speed on both, using a GPU server and a smartphone. Finally, we demonstrate that the type of damage can be classified into eight types with high accuracy by applying the proposed object detection method. The road damage data set, our experimental results, and the developed smartphone application used in this study are publicly available (https://github.com/sekilab/RoadDamageDetector/).
Article
Full-text available
The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. Organised annually from 2005 to present, the challenge and its associated dataset has become accepted as the benchmark for object detection. This paper describes the dataset and evaluation procedure. We review the state-of-the-art in evaluated methods for both classification and detection, analyse whether the methods are statistically different, what they are learning from the images (e.g. the object or its context), and what the methods find easy or confuse. The paper concludes with lessons learnt in the three year history of the challenge, and proposes directions for future improvement and extension.
Article
Many municipalities and road authorities seek to implement automated evaluation of road damage. However, they often lack technology, know-how, and funds to afford state-of-the-art equipment for data collection and analysis of road damages. Although some countries, like Japan, have developed less expensive and readily available Smartphone-based methods for automatic road condition monitoring, other countries still struggle to find efficient solutions. This work makes the following contributions in this context. Firstly, it assesses usability of Japanese model for other countries. Secondly, it proposes a large-scale heterogeneous road damage dataset comprising 26,620 images collected from multiple countries (India, Japan, and the Czech Republic) using smartphones. Thirdly, it proposes models capable of detecting and classifying road damages in more than one country. Lastly, the study provides recommendations for readers, local agencies, and municipalities of other countries when one other country publishes its data and model for automatic road damage detection and classification. A part of the proposed dataset was utilized for Global Road Damage Detection Challenge’2020 and can be accessed at (https://github.com/sekilab/RoadDamageDetector/).
Article
The Pascal Visual Object Classes (VOC) challenge consists of two components: (i) a publicly available dataset of images together with ground truth annotation and standardised evaluation software; and (ii) an annual competition and workshop. There are five challenges: classification, detection, segmentation, action classification, and person layout. In this paper we provide a review of the challenge from 2008–2012. The paper is intended for two audiences: algorithm designers, researchers who want to see what the state of the art is, as measured by performance on the VOC datasets, along with the limitations and weak points of the current generation of algorithms; and, challenge designers, who want to see what we as organisers have learnt from the process and our recommendations for the organisation of future challenges. To analyse the performance of submitted algorithms on the VOC datasets we introduce a number of novel evaluation methods: a bootstrapping method for determining whether differences in the performance of two algorithms are significant or not; a normalised average precision so that performance can be compared across classes with different proportions of positive instances; a clustering method for visualising the performance across multiple algorithms so that the hard and easy images can be identified; and the use of a joint classifier over the submitted algorithms in order to measure their complementarity and combined performance. We also analyse the community’s progress through time using the methods of Hoiem et al. (Proceedings of European Conference on Computer Vision, 2012) to identify the types of occurring errors. We conclude the paper with an appraisal of the aspects of the challenge that worked well, and those that could be improved in future challenges.
Transfer learning-based road damage detection for multiple countries
  • D Arya
  • H Maeda
  • S K Ghosh
  • D Toshniwal
  • A Mraz
  • T Kashiyama
  • Y Sekimoto
D. Arya, H. Maeda, S. K. Ghosh, D. Toshniwal, A. Mraz, T. Kashiyama, and Y. Sekimoto, "Transfer learning-based road damage detection for multiple countries," arXiv preprint arXiv:2008.13101, 2020.