FasterRCNN Monitoring of Road Damages: Competition and Deployment

Hascoet, Tristan; Zhang, Yihao; Persch, Andreas; Takashima, Ryoichi; Takiguchi, Tetsuya; Ariki, Yasuo

doi:10.1109/bigdata50022.2020.9377871

Cited by 12 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On both the training and the testing datasets, the model generated some false positives when there was no road damage. The calculated F1 score is 0.853, which is better than the performance of the networks for the same purpose in[19][20][21][22][23][24]. Overall, the results show that the trained YOLO model is especially good at telling cracks from potholes, but can sometimes make mistakes in distinguishing undamaged roads from damage.…”

mentioning

confidence: 84%

See 1 more Smart Citation

Cloud-Based Collaborative Road-Damage Monitoring with Deep Learning and Smartphones

et al. 2022

View full text Add to dashboard Cite

Road damage such as potholes and cracks may reduce ride comfort and traffic safety. This influence can be prevented by regular, proper monitoring and maintenance of roads. Traditional methods and existing methods of surveying are very time-consuming, expensive, require a lot of human effort, and, thus, cannot be conducted frequently. A more efficient and cost-effective process is required to augment profilometer and traditional road-condition recognition systems. In this study, we propose deep-learning methods using smartphone data to devise a cost-effective and ad-hoc approach. Information from sensors on smartphones such as motion sensors and cameras are harnessed to detect road damage using deep-learning algorithms. In order to give heuristic and accurate information about the road damage, we used a cloud-based collaborative approach to fuse all the data and update a map frequently with these road-surface conditions. During the experiment, the deep-learning models achieved good prediction accuracy on our dataset, and the cloud-based fusion approach was able to group and merge the detections from different vehicles.

show abstract

mentioning

confidence: 84%

“…The authors of [20] used a variant of Fast R-CNN, the bi-directional feature pyramid network (BiFPN), and achieved an F1 score of 0.6455. Other participating teams also used variants of YOLO [21,22] or R-CNN [23,24], and their F1 scores were between 0.5 and 0.66.…”

Section: Related Workmentioning

confidence: 99%

Cloud-Based Collaborative Road-Damage Monitoring with Deep Learning and Smartphones

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Deep learning methods, such as Fast R-CNN [1], Faster R-CNN [2], and Cascade RCNN [3], are commonly used for crack detection. Various detection models [4][5][6] apply these methods. Pei et al [7] applied the Cascade RCNN and introduced a consistency filtering mechanism, leveraging self-supervised learning to make the most of unlabeled data.…”

Section: Crack Detectionmentioning

confidence: 99%

Auxcoformer: Auxiliary and Contrastive Transformer for Robust Crack Detection in Adverse Weather Conditions

Yoon,

Jung,

Yoo

2024

Mathematics

View full text Add to dashboard Cite

Crack detection is integral in civil infrastructure maintenance, with automated robots for detailed inspections and repairs becoming increasingly common. Ensuring fast and accurate crack detection for autonomous vehicles is crucial for safe road navigation. In these fields, existing detection models demonstrate impressive performance. However, they are primarily optimized for clear weather and struggle with occlusions and brightness variations in adverse weather conditions. These problems affect automated robots and autonomous vehicle navigation that must operate reliably in diverse environmental conditions. To address this problem, we propose Auxcoformer, designed for robust crack detection in adverse weather conditions. Considering the image degradation caused by adverse weather conditions, Auxcoformer incorporates an auxiliary restoration network. This network efficiently restores damaged crack details, ensuring the primary detection network obtains better quality features. The proposed approach uses a non-local patch-based 3D transform technique, emphasizing the characteristics of cracks and making them more distinguishable. Considering the connectivity of cracks, we also introduce contrastive patch loss for precise localization. Then, we demonstrate the performance of Auxcoformer, comparing it with other detection models through experiments.

show abstract

“…The second category is the object detection, which determines the road damage in very fine resolution imagery using a detection box [34], [35], [36]. It includes the one-step methods that directly detect the damage [9], [37], [38], and the two-step methods that use a detection step following classification [39], [40], [41], [42]. These methods generally used rectangular boxes to locate the detected damaged objects.…”

Section: B Deep Learningmentioning

confidence: 99%

A New Method for Automated Monitoring of Road Pavement Aging Conditions Based on Recurrent Neural Network

Chen

Zhang

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

The automated monitoring of road pavement conditions is a challenging subject in intelligent transportation. However, the existing studies mostly focus on extracting pavement damages such as cracks, while the pavement aging conditions are still less investigated. In this paper, a novel method based on a modified recurrent neural network is designed for automated monitoring of asphalt pavement aging phenomena from fineresolution satellite imagery. A spectral augmentation method is proposed to enhance the spectral details of the road pavements. A novel loss function is also proposed to improve the bi-directional gated recurrent unit (Bi-GRU) network in order to better classify different degrees of road pavement aging and nonpavement objects. In order to demonstrate the outperformance of the modified network Bi-GRU+, the Worldview-2 satellite image (16360 * 7728) covering 16 asphalt roads in the southwestern suburb of Beijing City is used. The results show that the proposed approach has better performance than existing machine learning methods, with an overall accuracy of 98.16% and a Kappa coefficient of 0.97. The overall processing time of the proposed method is 7836 seconds in our case study. The proposed method is efficient for large-scale monitoring of road health conditions from fine-resolution satellite imagery. It can become a part of intelligent transportation and provide a new foundation for largerange automated monitoring of road pavement aging conditions.

show abstract

FasterRCNN Monitoring of Road Damages: Competition and Deployment

Cited by 12 publications

References 9 publications

Cloud-Based Collaborative Road-Damage Monitoring with Deep Learning and Smartphones

Cloud-Based Collaborative Road-Damage Monitoring with Deep Learning and Smartphones

Auxcoformer: Auxiliary and Contrastive Transformer for Robust Crack Detection in Adverse Weather Conditions

A New Method for Automated Monitoring of Road Pavement Aging Conditions Based on Recurrent Neural Network

Contact Info

Product

Resources

About