Field study toward anomaly road damage detection with drive recorder



Published Sep 4, 2023
Masato Tsuchiya Ken Miyamoto Takashi Ota Yasushi Sugama


As one of the ways to reduce road maintenance costs, road damage detection with a mobile camera is gaining attention. Most of conventional damage detection use supervised learning, nevertheless three practical drawbacks exist. Firstly, supervised learning requires a high manual cost to collect annotated data for training. Secondly, some damages are rarely observed, resulting in imbalanced data and difficulty in training an efficient model for all damage categories. Additionally, annotators may not identify such rare damages correctly. Thirdly, supervised learning cannot detect unknown categories of damages, though unknown categories are often found in a practical scene. To overcome these three drawbacks, we propose an ensemble model that combines anomaly detection and supervised damage detection. Anomaly detection can detect previously unknown and rare types of damage, while supervised damage detection ensures damages frequently observed on roads. Two different models cover wider categories of road damages. Our ensemble model is expected to achieve higher accuracy and lower manual cost.  

Abstract 140 | PDF Downloads 136



object detection, anomaly detection, road defect detection

Akcay, S., Atapour-Abarghouei, A., & Breckon, T. P. (2019). Ganomaly: Semi-supervised anomaly detection via adversarial training. In Computer vision–accv 2018: 14th asian conference on computer vision, perth, australia, december 2–6, 2018, revised selected papers, part iii 14 (pp. 622–637).

Bukhsh, Z. A., Jansen, N., & Saeed, A. (2021). Damage detection using in-domain and cross-domain transfer learning. Neural Computing and Applications, 33(24), 16921–16936.

Defard, T., Setkov, A., Loesch, A., & Audigier, R. (2021). Padim: a patch distribution modeling framework for anomaly detection and localization. In Pattern recognition. icpr international workshops and challenges: Virtual event, january 10–15, 2021, proceedings, part iv (pp. 475–489).

Dwibedi, D., Misra, I., & Hebert, M. (2017). Cut, paste and learn: Surprisingly easy synthesis for instance detection. In Proceedings of the ieee international conference on computer vision (pp. 1301–1310).

Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430.

Hegde, V., Trivedi, D., Alfarrarjeh, A., Deepak, A., Kim, S. H., & Shahabi, C. (2020). Yet another deep learning approach for road damage detection using ensemble learning. In 2020 ieee international conference on big data (big data) (pp. 5553–5558).

Jo, Y., & Ryu, S. (2015). Pothole detection system using a black-box camera. Sensors, 15(11), 29316–29331.

Lee, S., Lee, S., & Song, B. C. (2022). Cfa: Coupled-hypersphere-based feature adaptation for target-oriented anomaly localization. IEEE Access, 10, 78446–78454.

Maeda, H., Sekimoto, Y., Seto, T., Kashiyama, T., & Omata, H. (2018). Road damage detection and classification using deep neural networks with smartphone images. Computer-Aided Civil and Infrastructure Engineering, 33(12), 1127–1141.

Nienaber, S., Booysen, M. J., & Kroon, R. (2015). Detecting potholes using simple image processing techniques and real-world footage.

Rudolph, M., Wehrbein, T., Rosenhahn, B., & Wandt, B. (2022). Fully convolutional cross-scale-flows for image-based defect detection. In Proceedings of the ieee/cvf winter conference on applications of computer vision (pp. 1088–1097).

Solovyev, R., Wang, W., & Gabruseva, T. (2021). Weighted boxes fusion: Ensembling boxes from different object detection models. Image and Vision Computing, 107, 104117.

Tao, X., Zhang, D., Wang, Z., Liu, X., Zhang, H., & Xu, D. (2018). Detection of power line insulator defects using aerial images analyzed with convolutional neural networks. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50(4), 1486–1498.

Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). Yolov7: Trainable bag-of-freebies sets new state-oftheart for real-time object detectors. arXiv preprint arXiv:2207.02696.

Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2021). You only learn one representation: Unified network for multiple tasks. arXiv preprint arXiv:2105.04206.

Xu, J., Xiong, Z., & Bhattacharyya, S. P. (2022). Pidnet: A real-time semantic segmentation network inspired from pid controller. arXiv preprint arXiv:2206.02066.

Zhao, H., Zhang, H., & Zhao, Y. (2023). Yolov7-sea: Object detection of maritime uav images based on improved yolov7. In Proceedings of the ieee/cvf winter conference on applications of computer vision (pp. 233– 238).
Special Session Papers