An Improved Lightweight Model for Defect Detection on Paths in Images
Source abstract
Abstract
To address the challenges of detecting multi-scale road defects and the lack of lightweight designs in conventional detection models, we propose ACD-YOLOv8, an enhanced model based on YOLOv8s. Our model enhances baseline architecture by integrating three key components: a lightweight Cross-Scale Feature Fusion Module (CCFM), an ADown sampling operation, and a Dynamic Head (DyHead). Experimental results on the RDD2022 dataset demonstrate the superiority of our approach. Compared to the baseline YOLOv8s, ACD-YOLOv8 achieves a 0.9% increase in mAP@0.5 and a 1.6% increase in the more stringent mAP@0.5:0.95 metric. Simultaneously, the model’s parameter count is reduced by 3.72 million (a 33.3% reduction) and its size is reduced by 7.4 MB. This work provides a practical and scalable solution for deploying high-accuracy defect detection on resource-constrained mobile platforms, offering significant potential to enhance traffic safety and maintenance efficiency.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Infrastructure Maintenance and Monitoring · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Architecture and Urban Planning, Beijing University of Civil Engineering and Architecture, Beijing 100044, China
Funding
National Natural Science Foundation of China · Beijing Nova Program
References (35)
Show source-provided references
1. (2024, August 03). World Bicycle Day | Road Bicycle Sales Soar by 200%! Outdoor Cycling Category Sees 40% Increase in Sales. Available online: https://baijiahao.baidu.com/s?id=1767670936258805255.
2. Road safety research in China: Review and appraisal10.1080/15389581003754593 ↗
3. Literature Review of Road Damage Detection with Repairing Cost Estimation
4. Sari, Y., Prakoso, P.B., and Baskara, A.R. (2019, January 18–21). Road Crack Detection using Support Vector Machine (SVM) and OTSU Algorithm. Proceedings of the 2019 6th International Conference on Electric Vehicular Technology (ICEVT), Bali, Indonesia.10.1109/ICEVT48285.2019.8993969 ↗
5. From global challenges to local solutions: A review of cross-country collaborations and winning strategies in road damage detection10.1016/j.aei.2024.102388 ↗
6. Wang, X., Gao, H., Jia, Z., and Li, Z. (2023). BL-YOLOv8: An Improved Road Defect Detection Model Based on YOLOv8. Sensors, 23.10.3390/s23208361 ↗
7. Pavement Defect Detection Algorithm Based on Improved YOLOv7 Complex Background10.1109/ACCESS.2024.3370604 ↗
8. Liu, Y., Duan, M., Ding, G., Ding, H., Hu, P., and Zhao, H. (2023). HE-YOLOv5s: Efficient Road Defect Detection Network. Entropy, 25.10.3390/e25091280 ↗
9. ADNet: Anti-noise Dual-Branch Network for Road Defect Detection10.1016/j.engappai.2024.107963 ↗
10. Jiang, Y., Yan, H., Zhang, Y., Wu, K., Liu, R., and Lin, C. (2023). Rdd-YOLOv5: Road Defect Detection Algorithm with Self-Attention Based on Unmanned Aerial Vehicle Inspection. Sensors, 23.10.3390/s23198241 ↗
11. SPCNet: A Strip Pyramid ConvNeXt Network for Detection of Road Surface Defects10.1007/s11760-023-02698-6 ↗
12. Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024). YOLOv10: Real-time End-to-End Object Detection. arXiv.
13. A review of YOLO object detection based on deep learning
14. 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 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
15. Arya, D., Maeda, H., Ghosh, S.K., Toshniwal, D., Omata, H., Kashiyama, T., and Sekimoto, Y. (2022, January 17–20). Crowdsensing-Based Road Damage Detection Challenge (CRDDC’2022). Proceedings of the 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan.10.1109/BigData55660.2022.10021040 ↗
16. Wang, C.-Y., Bochkovskiy, A., and Liao, H.-Y.M. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
17. Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
18. Li, H., Xiong, P., An, J., and Wang, L. (2018). Pyramid attention network for semantic segmentation. arXiv.
19. Feng, C., Zhong, Y., Gao, Y., Scott, M.R., and Huang, W. (2021, January 10–17). Tood: Task-aligned one-stage object detection. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00349 ↗
20. Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., and Chen, J. (2024, January 17–21). DETRs Beat YOLOs on Real-Time Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.01605 ↗
21. Wang, C.Y., Yeh, I.H., and Liao, H.Y.M. (2024). YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. arXiv.10.1007/978-3-031-72751-1_1 ↗
22. Liu, R., Huang, M., Wang, L., Bi, C., and Tao, Y. (2024). PDT-YOLO: A Roadside Object-Detection Algorithm for Multiscale and Occluded Targets. Sensors, 24.10.3390/s24072302 ↗
23. UAV dense small target detection algorithm based on YOLOv5s
24. Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.
25. Huang, D.S., Zhang, X., and Guo, J. (2024). AYOLOv8: Improved Detector Based on YOLOv8 to Focus More on Small and Medium Objects. Advanced Intelligent Computing Technology and Applications, Springer. ICIC 2024.
26. Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., and Zhang, L. (2021, January 20–25). Dynamic Head: Unifying Object Detection Heads with Attentions. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00729 ↗
27. Zhang, Y., Su, X., and Ma, M. (2024). MA-YOLOv8 Algorithm for Mining Area Object Detection Based on High-Resolution Remote Sensing Images, Springer Nature.10.1007/978-981-97-5675-9_28 ↗
28. Wang, J., Meng, R., Huang, Y., Zhou, L., Huo, L., Qiao, Z., and Niu, C. (2024). Road defect detection based on improved YOLOv8s model. Sci. Rep., 14.10.1038/s41598-024-67953-3 ↗
29. RDD2022: A multi-national image dataset for automatic road damage detection
30. Tan, M., Pang, R., and Le, Q.V. (2020, January 13–19). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01079 ↗
31. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv.
32. Ouyang, H. (2023). DEYOv3: DETR with YOLO for Real-time Object Detection. arXiv.
33. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
34. Zhang, Y., Sun, Y., Wang, Z., and Jiang, Y. (2023). YOLOv7-RAR for Urban Vehicle Detection. Sensors, 23.10.3390/s23041801 ↗
35. Huang, L., and Huang, W. (2022). RD-YOLO: An Effective and Efficient Object Detector for Roadside Perception System. Sensors, 22.10.3390/s22218097 ↗