A New Road Damage Detection Baseline with Attention Learning
Source abstract
Abstract
Automated detection of road damage (ADRD) is a challenging topic in road maintenance. It focuses on automatically detecting road damage and assessing severity by deep learning. Because of the sparse distribution of characteristic pixels, it is more challenging than object detection. Although some public datasets provide a database for the development of ADRD, their amounts of data and the standard of classification cannot meet network training and feature learning. With the aim of solving this problem, this work publishes a new road damage dataset named CNRDD, which is labeled according to the latest evaluation standard for highway technical conditions in China (JTG5210-2018). The dataset is collected by professional onboard cameras and is manually labeled in eight categories with three different degrees (mild, moderate and severe), which can effectively help promote research of automated detection of road damage. At the same time, a novel baseline with attention fusion and normalization is proposed to evaluate and analyze the published dataset. It explicitly leverages edge detection cues to guide attention for salient regions and suppresses the weights of non-salient features by attention normalization, which can alleviate the interference of sparse pixel distribution on damage detection. Experimental results demonstrate that the proposed baseline significantly outperforms most existing methods on the existing RDD2020 dataset and the newly released CNRDD dataset. Further, the CNRDD dataset is proved more robust, as its high damage density and professional classification are more conducive to promote the development of ADRD.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Asphalt Pavement Performance Evaluation · Occupational Health and Safety Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Inner Mongolia Autonomous Region Traffic Construction Engineering Quality Supervision Bureau, Hohhot 010051, China
Key Laboratory of Transport Industry of Management, Control and Cycle Repair Technology for Traffic Network Facilitates in Ecological Security Barrier Area, Hohhot 010051, China
China Academy of Transportation Sciences, Beijing 100029, China
College of Information Engineering, Capital Normal University, Beijing 100048, China
Funding
The Open Fund of Key Laboratory of Transportation Industry · Natural Science Foundation of Inner Mongolia Autonomous Region
References (42)
Show source-provided references
1. Yu, B., Tang, M., Zhu, G., Wang, J., and Lu, H. (2021). Enhanced Bounding Box Estimation with Distribution Calibration for Visual Tracking. Sensors, 21.10.3390/s21238100 ↗
2. Fang, K., Ouyang, J., and Hu, B. (2021). Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images. Sensors, 21.10.3390/s21238113 ↗
3. Arya, D., Maeda, H., Ghosh, S.K., Toshniwal, D., Mraz, A., Kashiyama, T., and Sekimoto, Y. (2020). Transfer learning-based road damage detection for multiple countries. arXiv.10.1016/j.autcon.2021.103935 ↗
4. Naddaf-Sh, S., Naddaf-Sh, M.M., Zargarzadeh, H., and Kashanipour, A.R. (2020). An Efficient and Scalable Deep Learning Approach for Road Damage Detection. arXiv.10.1109/BigData50022.2020.9377751 ↗
5. Arya, D., Maeda, H., Ghosh, S.K., Toshniwal, D., Omata, H., Kashiyama, T., and Sekimoto, Y. (2020, January 10–13). Global Road Damage Detection: State-of-the-art Solutions. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377790 ↗
6. Zhang, X., Xia, X., Li, N., Lin, M., and Ding, N. (2020, January 10–13). Exploring the Tricks for Road Damage Detection with A One-Stage Detector. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377923 ↗
7. Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network10.1111/mice.12297 ↗
8. Unified Approach to Pavement Crack and Sealed Crack Detection Using Preclassification Based on Transfer Learning10.1061/(ASCE)CP.1943-5487.0000736 ↗
9. Mandal, V., Mussah, A.R., and Adu-Gyamfi, Y. (2020, January 10–13). Deep Learning Frameworks for Pavement Distress Classification: A Comparative Analysis. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9378047 ↗
10. Zhang, Y., Wang, X., Xie, X., and Li, Y. (2018). Salient Object Detection via Recursive Sparse Representation. Remote Sens., 10.10.3390/rs10040652 ↗
11. Girshick, R. (2015, January 7–13). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.169 ↗
12. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv.
13. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
14. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
15. Jocher, G., Stoken, A., Borovec, J., Changyu, L., CoImagro, A., Ye, H., and Poznanski, J. (2021, January 05). yolov5: v4.0. Available online: https://zenodo.org/record/4418161#.YuILYepByUk.
16. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
17. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
18. Tian, Z., Shen, C., Chen, H., and He, T. (November, January 27). FCOS: Fully Convolutional One-Stage Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea.
19. Caroff, G., Joubert, P., Prudhomme, F., and Soussain, G. (, January February). Classification of pavement distresses by image processing (MACADAM SYSTEM). Proceedings of the 1st International Conference on Applications of Advanced Technologies in Transportation Engineering ASCE, San Diego, CA, USA.
20. Road crack detection using visual features extracted by Gabor filters10.1111/mice.12042 ↗
21. Evaluating pavement cracks with bidimensional empirical mode decomposition
22. Oliveira, H., and Correia, P.L. (2009, January 24–28). Automatic road crack segmentation using entropy and image dynamic thresholding. Proceedings of the IEEE 17th European Signal Processing Conference, Glasgow, UK.
23. Wang, K.C., Hou, Z., and Gong, W. (2008, January 23–28). Automation techniques for digital highway data vehicle (DHDV). Proceedings of the 7th International Conference on Managing Pavement Assets, Calgary, AB, Canada.
24. Zhang, L., Yang, F., Zhang, Y.D., and Zhu, Y.J. (2016, January 25–28). Road crack detection using deep convolutional neural network. Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.10.1109/ICIP.2016.7533052 ↗
25. Eisenbach, M., Stricker, R., Seichter, D., Amende, K., Debes, K., Sesselmann, M., Ebersbach, D., Stoeckert, U., and Gross, H.-M. (2017, January 14–19). How to get pavement distress detection ready for deep learning? A systematic approach. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.10.1109/IJCNN.2017.7966101 ↗
26. Pavement image datasets: A new benchmark dataset to classify and densify pavement distresses10.1177/0361198120907283 ↗
27. Generative adversarial network for road damage detection10.1111/mice.12561 ↗
28. A review of three dimensional imaging technologies for pavement distress detection and measurements10.1109/TITS.2015.2428655 ↗
29. Wang, Y.J., Ding, M., Kan, S., Zhang, S., and Lu, C. (2018, January 10–13). Deep proposal and detection networks for road damage detection and classification. Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.10.1109/BigData.2018.8622599 ↗
30. Concrete cracks detection based on deep learning image classification
31. Pixel-level cracking detection on 3D asphalt pavement images through deep-learning-based CrackNet-V10.1109/TITS.2019.2891167 ↗
32. A computational approach to edge detection10.1109/TPAMI.1986.4767851 ↗
33. Liu, Y., Shao, Z., Teng, Y., and Hoffmann, N. (2021, September 28). NAM: Normalization-based Attention Module. NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future. Available online: https://openreview.net/forum?id=AaTK_ESdkjg.
34. Hegde, V., Trivedi, D., Alfarrarjeh, A., Deepak, A., Kim, S.H., and Shahabi, C. (2020, January 10–13). Yet Another Deep Learning Approach for Road Damage Detection using Ensemble Learning. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377833 ↗
35. Doshi, K., and Yilmaz, Y. (2020, January 10–13). Road Damage Detection using Deep Ensemble Learning. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377774 ↗
36. Pei, Z., Lin, R., Zhang, X., Shen, H., Tang, J., and Yang, Y. (2020, January 10–13). CFM: A Consistency Filtering Mechanism for Road Damage Detection. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377911 ↗
37. Hascoet, T., Zhang, Y., Persch, A., Takashima, R., Takiguchi, T., and Ariki, Y. (2020, January 10–13). FasterRCNN Monitoring of Road Damages: Competition and Deployment. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377871 ↗
38. Vishwakarma, R., and Vennelakanti, R. (2020, January 10–13). CNN Model & Tuning for Global Road Damage Detection. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377902 ↗
39. Pham, V., Pham, C., and Dang, T. (2020, January 10–13). Road Damage Detection and Classification with Detectron2 and Faster R-CNN. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9378027 ↗
40. Kortmann, F., Talits, K., Fassmeyer, P., Warnecke, A., Meier, N., Heger, J., Drews, P., and Funk, B. (2020, January 10–13). Detecting Various Road Damage Types in Global Countries Utilizing Faster R-CNN. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9378245 ↗
41. Jeong, D. (2020, January 10–13). Road Damage Detection Using YOLO with Smartphone Images. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377847 ↗
42. Liu, Y., Zhang, X., Zhang, B., and Chen, Z. (2020, January 10–13). Deep Network For Road Damage Detection. Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA.10.1109/BigData50022.2020.9377991 ↗