改进YOLOV5s的铁轨裂纹目标检测算法

doi:10.3778/j.issn.1002-8331.2306-0011

摘要/Abstract

摘要： 铁轨表面的裂纹图像目标小、背景干扰信息多、分辨率高，使其目标检测效果并不理想。对此，提出一种改进YOLOV5s的目标检测算法以提升铁轨裂纹的检测效果。在颈部网络中引入VOV-GSCSP模块，用更轻量的卷积方式GSconv来替换普通的卷积，在保留更多细节信息的同时减轻网络的计算量。改进特征金字塔结构，提出多路径跨层融合结构，在特征金字塔下采样的过程中跨层融入主干网络的信息，保留更多原始的特征信息，提升目标检测的精度。同时，引入CA注意力模块和Transformer结构进一步加强高阶语义的信息提取。实验结果表明，改进的YOLOV5s算法，平均均值精度（mAP）达到62.4%，相对于原YOLOV5s算法提高了6.2个百分点；召回率（Recall）为92.2%，提升了4.4个百分点。

关键词: 目标检测, YOLOV5, GSconv, 注意力机制

Abstract: The crack image on the rail surface has a small target, many background interference information and a high resolution, making its target detection effect not ideal. In this regard, the paper proposes an improved target detection algorithm of YOLOV5s to improve the detection effect of rail cracks. The VOV-GSCSP module is introduced in the neck network, and the ordinary convolution is replaced by the lighter convolution method GSconv to reduce the computational effort of the network while retaining more detailed information. The feature pyramid structure is improved and a multi-path cross-layer fusion structure is proposed to incorporate the information of the backbone network across layers in the process of feature pyramid downsampling to retain more original feature information and improve the accuracy of target detection. Meanwhile, the CA attention module and Transformer structure are introduced to further enhance the information extraction of higher-order semantics. The experimental results show that the improved YOLOV5s algorithm achieves an average mean accuracy (mAP) of 62.4%, which is 6.2 percentage points better than the original YOLOV5s algorithm; the recall rate (Recall) is 92.2%, which is 4.4 percentage points better.

Key words: target detection, YOLOV5, GSconv, attention mechanism

苗新法, 刘宝莲, 李晓琴, 侯越. 改进YOLOV5s的铁轨裂纹目标检测算法[J]. 计算机工程与应用, 2024, 60(12): 216-224.

MIAO Xinfa, LIU Baolian, LI Xiaoqin, HOU Yue. Improved YOLOV5s Railway Crack Target Detection Algorithm[J]. Computer Engineering and Applications, 2024, 60(12): 216-224.

参考文献

[1] 曾志平, 申石文, 涂勤明, 等. 桥上双块式无砟轨道床板防裂优化设计研究[J]. 铁道工程学报, 2019, 36(7): 19-26.
ZENG Z P, SHEN S W, TU Q M, et al. Research on the anti-cracking optimization design of bed slabs for double-block ballastless track on bridge[J]. Journal of Railway Engineering Society, 2019, 36 (7): 19-26.
[2] GIRSHICK R. Fast R-CNN[C]//IEEE International Conference on Computer Vision (ICCV), Santiago Chile, December 7-13, 2015. New York: IEEE, 2015: 1440-1448.
[3] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 779-788.
[4] REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[5] BOCHKOVSKIY A, WANG C, LIAO H M. Yolov4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[6] 杨睿宁, 惠飞, 金鑫, 等. 改进YOLOv5s的复杂交通场景路侧目标检测算法[J]. 计算机工程与应用, 2023, 59(16): 159-169.
YANG R N, HUI F, JIN X, et al. Roadside target detection algorithm for complex traffic scene based on improved YOLOv5s[J]. Computer Engineering and Applications, 2023, 59(16): 159-169.
[7] 李冰涛, 李大海. 面向小目标的YOLOv5s安全帽佩戴检测[J]. 计算机系统应用, 2023, 32(8): 221-229.
LI B T, LI D H. YOLOv5s-based helmet wearing detection for small targets[J]. Computer Systems & Applications, 2023, 32(8): 221-229.
[8] 白堂博, 高嘉琳, 杨建伟, 等. 基于改进Mask R-CNN的铁路扣件状态检测方法研究[J]. 铁道建筑, 2021, 61(6): 140-143.
BAI T B, GAO J L, YANG J W, et al. Research on railway fastener status inspection method based on improved Mask R-CNN[J]. Railway Engineering, 2021, 61(6): 140-143.
[9] AYDIN I, AKIN E, KARAKOSE M. Defect classification based on deep features for railway tracks in sustainable transportation[J]. Applied Soft Computing, 2021, 111: 107706.
[10] 吴送英, 刘林芽, 张洪, 等. 基于迁移学习的铁路扣件缺陷形态检测算法研究[J]. 铁道科学与工程学报, 2022, 19(12): 3612-3624.
WU S Y, LIU L Y, ZHANG H, et al. Research on defect morphology detection algorithm of railway fastener based on Transfer learning[J]. Journal of Railway Science and Engineering, 2022, 19(12): 3612-3624.
[11] WAN Z J, CHEN S Q. Railway tracks defects detection based on deep convolution neural networks[M]//Artificial intelligence in China. Singapore: Springer, 2021: 119-129.
[12] 崔晓宁, 王起才, 李盛, 等. 基于YOLOv5的双块式轨枕裂缝智能识别[J]. 铁道学报, 2022, 44(4): 104-111.
CUI X N, WANG Q C, LI S, et al. Intelligent recognition of cracks in doubleblock sleeper based on YOLOv5[J]. Journal of the China Railways Society, 2022, 44(4): 104-111.
[13] 周淼森, 汤全武, 石甜甜, 等. 基于改进YOLOv5s的铁轨表面裂纹检测算法[J]. 液晶与显示, 2023, 38(5): 666-679.
ZHOU M S, TANG Q W, SHI T T, et al. Rail surface crack detection algorithm based on improved YOLOv5s[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(5): 666-679.
[14] LI H, LI J, WEI H, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[J]. arXiv:2206.02424, 2022.
[15] 陈一潇, 阿里甫·库尔班, 林文龙, 等. 面向拥挤行人检测的CA-YOLOv5[J]. 计算机工程与应用, 2022, 58(9): 238-245.
CHEN Y X, Alifu Kurban, LIN W L, et al. CA-YOLOv5 for congested pedestrian detection[J]. Computer Engineering and Applications, 2022, 58(9): 238-245.
[16] IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning, 2015: 448-456.
[17] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117-2125.
[18] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-876.
[19] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
[20] MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[J]. arXiv:1807.11164, 2018.
[21] TAN M, PANG R, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 10781-10790.
[22] 李国豪, 袁一帆, 贲晛烨, 等. 采用时空注意力机制的人脸微表情识别[J]. 中国图象图形学报, 2020, 25(11): 2380-2390.
LI G H, YUAN Y F, BEN X Y, et al. Spatiotemporal attention network for microexpression recognition[J]. Journal of Image and Graphics, 2020, 25(11): 2380-2390.
[23] JIE H, LI S, GANG S. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018.
[24] WU W, ZHANG Y, WANG D, et al. SK-Net: deep learning on point cloud via end-to-end discovery of spatial keypoints[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 6422-6429.
[25] WANG Q, WU B, ZHU P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, WA, USA, June 13-19 2020: 11531-11539.
[26] WOO S, PARK J, LEE J Y, et al. Cbam: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.
[27] FU J, LIU J, TIAN H, et al. Dual attention network for scene segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 3146-3154.
[28] HUANG Z, WANG X, HUANG L, et al. Ccnet: criss-cross attention for semantic segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 603-612.
[29] ZHU X, LYU S, WANG X, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 2778-2788.
[30] 孙伟凯. 基于深度学习的高分辨率图像裂缝检测研究[D]. 济南: 山东大学, 2021.
SUN W K. Research on crack detection in high resolution image based on deep learning [D]. Jinan: Shandong University, 2021.