|
|
YOLOv5-W桥梁裂纹实时检测算法
|
Abstract:
桥梁的定期检修与维护，是保证交通安全、保障桥梁使用年限的重要措施。在桥梁的诸多损伤中，桥梁裂纹是最为普遍的损伤。针对现有裂纹研究中模型计算量大、实时性较差、需要大数据集训练等问题，提出了一种基于YOLOv5改进的YOLOv5-W模型。对YOLOv5的损失函数和颈部网络的设计进行了优化，使用Wise IoU，通过离群度来衡量检测框质量，做出最合适的梯度增益分配，提高检测精度。使用轻量化颈部Slim-Neck设计缩小模型的参数量，提高检测速度。在小数据集Crack400上验证表明，改进模型准确度为98.7，均值平均精度(mean average precision, MAP)为98.5，检测速度为47.958 FPS，模型参数减少到14.5 GPLOPs。相较于原始的YOLOv5，平均精度提升3%，FPS提升12，模型大小减小1.3 GFLOPs。
Regular maintenance and repair of bridges is an important measure to ensure traffic safety and to safeguard the service life of bridges. Among the many damages to bridges, bridge cracks are the most common damage. A YOLOv5-W model based on an improved YOLOv5 is proposed to address the problems of large model computation, poor real-time performance and the need for large data sets for training in existing cracking studies. The loss function of YOLOv5 and the design of the neck network are optimized, and Wise IoU is used to measure the quality of the detection frame by the outlier degree to make the most appropriate gradient gain assignment and improve the detection accuracy. A lightweight neck Slim-Neck design was used to reduce the number of parameters in the model and improve detection speed. Validation on the small dataset Crack400 shows that the im-proved model has an accuracy of 0.987, a mean average precision (mAP) of 0.985, a detection speed of 47.958 FPS and a reduction in model parameters to 14.5 GPLOPs. The model size was reduced by 1.3 GFLOPs.
| [1] | 赵建华. 断裂力学在桥梁裂纹检测分析中的应用[D]: [硕士学位论文]. 西安: 长安大学, 2008. |
| [2] | 王恩永. 道路桥梁养护存在的问题及其预防措施探讨[J]. 中国高新技术企业, 2013(8): 98-99. |
| [3] | Yeum, C.M. (2015) Vi-sion-Based Automated Crack Detection for Bridge. Computer-Aided Civil and Infrastructure Engineering, 30, 759-770. https://doi.org/10.1111/mice.12141 |
| [4] | Zhang, C., Wan, L., Wan, R.Q., Yu, J. and Li, R. (2022) Automated Fa-tigue Crack Detection in Steel Box Girder of Bridges Based on Ensemble Deep Neural Network. Measurement, 202, Ar-ticle ID: 111805.
https://doi.org/10.1016/j.measurement.2022.111805 |
| [5] | Dung, C.V., Sekiya, H., Hirano, S., et al. (2019) A Vi-sion-Based Method for Crack Detection in Gusset Plate Welded Joints of Steel Bridges Using Deep Convolutional Neu-ral Networks. Automation in Construction, 102, 217-229.
https://doi.org/10.1016/j.autcon.2019.02.013 |
| [6] | Jang, K., Jung, H. and An, Y.K. (2022) Automated Bridge Crack Evaluation through Deep Super Resolution Network-Based Hybrid Image Matching. Automation in Construction, 137, Article ID: 104229.
https://doi.org/10.1016/j.autcon.2022.104229 |
| [7] | 令雅莉, 杨桂芹, 张又元, 王小鹏. 基于改进算法YOLOv5+的混凝土轨枕裂纹检测[J]. 铁道标准设计, 2023: 1-10. https://doi.org/10.13238/j.issn.1004-2954.202210030001 |
| [8] | Ren, S., He, K., Girshick, R. and Sun, J. (2015) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149.
https://doi.org/10.1109/TPAMI.2016.2577031 |
| [9] | He, K., Gkioxari, G., Dollár, P. and Girshick, R. (2017) Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 2980-2988. https://doi.org/10.1109/ICCV.2017.322 |
| [10] | Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recog-nition (CVPR), Las Vegas, 27-30 June 2016, 779-788. https://doi.org/10.1109/CVPR.2016.91 |
| [11] | Redmon, J. and Farhadi, A. (2017) YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 6517-6525. https://doi.org/10.1109/CVPR.2017.690 |
| [12] | Liu, W., Anguelov, D., Erhan, D., et al. (2016) SSD: Single Shot MultiBox Detector. In: Leibe, B., Matas, J., Sebe, N. and Welling, M., Eds., ECCV 2016: Computer Vision—ECCV 2016, Springer, Cham, 21-37.
https://doi.org/10.1007/978-3-319-46448-0_2 |
| [13] | Haciefendio？lu, K. and Ba？a？a, H.B. (2022) Concrete Road Crack Detection Using Deep Learning-Based Faster R-CNN Method. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 46, 1621-1633.
https://doi.org/10.1007/s40996-021-00671-2 |
| [14] | Zhang, Y.X., Huang, J. and Cai, F.H. (2020) On Bridge Surface Crack Detection Based on an Improved YOLO v3 Algorithm. IFAC-PapersOnLine, 53, 8205-8210. https://doi.org/10.1016/j.ifacol.2020.12.1994 |
| [15] | Yu, Z., Shen, Y. and Shen, C. (2021) A Real-Time Detection Approach for Bridge Cracks Based on YOLOv4-FPM. Automation in Construction, 122, Article ID: 103514. https://doi.org/10.1016/j.autcon.2020.103514 |
| [16] | Zhang, J., Qian, S. and Tan, C. (2022) Automated Bridge Sur-face Crack Detection and Segmentation Using Computer Vision-Based Deep Learning Model. Engineering Applications of Artificial Intelligence, 115, Article ID: 105225.
https://doi.org/10.1016/j.engappai.2022.105225 |
| [17] | Mishra, M., Jain, V., Singh, S.K. and Maity, D. (2022) Two-Stage Method Based on the You Only Look Once Framework and Image Segmentation for Crack Detection in Concrete Structures. Architecture, Structures and Construction, 3, 429-446. https://doi.org/10.1007/s44150-022-00060-x |
| [18] | Zhang, Y.F., Ren, W.Q., Zhang, Z., Jia, Z., Wang, L. and Tan, T.N. (2022) Focal and Efficient IOU Loss for Accurate Bounding Box Regression. Neurocomputing, 506, 146-157. https://doi.org/10.1016/j.neucom.2022.07.042 |
| [19] | Lin, T.Y., Dollar, P., Girshick, R., et al. (2017) Feature Pyra-mid Networks for Object Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hon-olulu, 21-26 July 2017, 936-944.
https://doi.org/10.1109/CVPR.2017.106 |
| [20] | Wang, C.Y., Bochkovskiy, A. and Liao, H.Y.M. (2021) Scaled-YOLOv4: Scaling cross Stage Partial Network. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 13024-13033. https://doi.org/10.1109/CVPR46437.2021.01283 |
| [21] | Bochkovskiy, A., Wang, C.Y. and Liao, H.Y. (2020) YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv:2004.10934 |
| [22] | Liu, S., Qi, L., Qin, H., et al. (2018) Path Aggregation Network for Instance Segmentation. 2018 IEEE/CVF Conference on Computer Vision and Pat-tern Recognition, Salt Lake City, 18-23 June 2018, 8759-8768.
https://doi.org/10.1109/CVPR.2018.00913 |
| [23] | Yin, X., Sasaki, Y., Wang, W. and Shimizu, K. (2020) 3D Object Detection Method Based on YOLO and K-Means for Image and Point Clouds. arXiv:2005.02132 |
| [24] | Tong, Z.J., Chen, Y.H., Xu, Z.W. and Rong, Y.U. (2023) Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism. arXiv:2301.10051. https://doi.org/10.48550/arXiv.2301.10051 |
| [25] | Li, H., Li, J., Wei, H., et al. (2022) Slim-Neck by GSConv: A Better Design Paradigm of Detector Architectures for Autonomous Vehicles. arXiv:2206.02424 |
| [26] | Huang, G., Liu, Z., Van Der Maaten, L., et al. (2017) Densely Connected Convolutional Net-works. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 2261-2269.
https://doi.org/10.1109/CVPR.2017.243 |
| [27] | Liang, T., Wang, Y., Tang, Z., et al. (2021) OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 10190-10198. https://doi.org/10.1109/CVPR46437.2021.01006 |
| [28] | Lee, Y., Hwang, J.W., Lee, S., Bae, Y. and Park, J. (2019) An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection. 2019 IEEE/CVF Con-ference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, 16-17 June 2019, 752-760. https://doi.org/10.1109/CVPRW.2019.00103 |
| [29] | Jia, Z.G., Su, X., Ma, G.D., Dai, T.T. and Sun, J.B. (2023) Crack Identification for Marine Engineering Equipment Based on Improved SSD and YOLOv5. Ocean Engineering, 268, Article 113534.
https://doi.org/10.1016/j.oceaneng.2022.113534 |
| [30] | Ju, H.Y., Wei, L., Tighe, S., Zhai, J.Z., Xu, Z.C. and Chen, Y. (2019) Detection of Sealed and Unsealed Cracks with Complex Backgrounds Using Deep Convolutional Neural Network. Automation in Construction, 107, Article 102946.
https://doi.org/10.1016/j.autcon.2019.102946 |
| [31] | Kumar, P.S. and Kumar, N.K. (2023) Drone-Based Apple De-tection: Finding the Depth of Apples Using YOLOv7 Architecture with Multi-Head Attention Mechanism. Smart Agri-cultural Technology, 5, Article ID: 100311.
https://doi.org/10.1016/j.atech.2023.100311 |
| [32] | Wang, G., Chen, Y., An, P., et al. (2023) UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios. Sensors, 23, Arti-cle 7190. https://doi.org/10.3390/s23167190 |
