1.宁夏大学 物理与电子电气工程学院, 宁夏 银川 750021
2.宁夏沙漠信息智能感知重点实验室, 宁夏 银川 750021
[ "周淼森(1997—),男,山西忻州人,硕士研究生,2019年于吕梁学院获得学士学位,主要从事深度学习与图像处理方面的研究。E-mail:15535853634@163.com" ]
[ "汤全武(1965—),男,甘肃民勤人,硕士,教授,2004年于西安交通大学获得硕士学位,主要从事模式识别与图像处理方面的研究。E-mail:tangqw@ nxu.edu.cn" ]
扫 描 看 全 文
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 Miao-sen, TANG Quan-wu, SHI Tian-tian, et al. Rail surface crack detection algorithm based on improved YOLOv5s[J]. Chinese Journal of Liquid Crystals and Displays, 2023,38(5):666-679.
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. DOI: 10.37188/CJLCD.2022-0267.
ZHOU Miao-sen, TANG Quan-wu, SHI Tian-tian, et al. Rail surface crack detection algorithm based on improved YOLOv5s[J]. Chinese Journal of Liquid Crystals and Displays, 2023,38(5):666-679. DOI: 10.37188/CJLCD.2022-0267.
铁轨轨枕表面出现的裂纹可能对轨道交通造成安全隐患。针对铁轨裂纹检测的方法存在通用性差、精度低、召回率低的问题,提出一种基于改进YOLOv5s的铁轨裂纹检测算法YOLOv5s-CBE。首先将CA注意力模块分别加入主干C3模块以及C3与SPPF之间,从通道和空间两个维度捕获通道关系和位置信息,提高YOLOv5s主干网络特征提取能力。其次,在YOLOv5s的Neck部分,使用BiFPN融合不同尺度信息,获取拥有丰富语义信息的输出特征图;同时,加权双向特征融合金字塔结构通过引入权重调整不同尺度输入特征图对输出的贡献,优化特征融合效果,减少了卷积过程中特征信息的丢失,提高了检测精度。最后,将原YOLOv5s中损失函数CIoU改为EIoU。EIoU不仅考虑了中心点距离和纵横比,而且还考虑了预测框与真实框宽度和高度的真实差异,提高了锚框的预测精度。相较于原始网络YOLOv5s,YOLOv5s-CBE铁轨裂纹检测网络在自制铁轨裂纹数据集上,模型大小相较于基础网络YOLOv5s降低了1.0 MB,精度mAP提高了3.7%,召回率由73.5%提升到76.2%,不同尺寸裂纹的漏检现象减少,具有一定的优越性和实用价值。
Cracks on the surface of rail sleepers may cause hidden dangers to rail transit. Aiming at the problems of poor universality, low accuracy and low recall of rail crack detection methods, a rail crack detection algorithm YOLOv5s-CBE based on improved YOLOv5s is proposed. Firstly, the CA attention module is added to the backbone C3 module and between C3 and SPPF respectively to capture the channel relationship and location information from the two dimensions of channel and space, so as to improve the feature extraction capability of YOLOv5s backbone network. Secondly, in the neck part of YOLOv5s, BiFPN is used to fuse different scale information to obtain the output feature map with rich semantic information; At the same time, the weighted bi-directional feature fusion pyramid structure adjusts the contribution of input feature maps of different scales to the output by introducing weights, optimizes the feature fusion effect, reduces the loss of feature information in the convolution process, and improves the detection accuracy. Finally, the loss function CIoU in the original yolov5s is changed to EIoU. EIoU not only considers the distance and aspect ratio of the center point, but also considers the real difference in width and height between the prediction frame and the real frame, which improves the prediction accuracy of the anchor frame. Compared with the original network YOLOv5s, the model size of YOLOv5s-CBE rail crack detection network on the self-made rail crack data set is reduced by 1.0 MB, the accuracy mAP is increased by 3.7%, the recall rate is increased from 73.5% to 76.2%, and the phenomenon of missing detection of cracks of different sizes is reduced. It has certain advantages and practical value.
铁轨裂纹YOLOv5s坐标注意力机制特征融合损失函数
rail crackYOLOv5scoordinate attention mechanismfeature fusionloss function
FAGHIH-ROOHI S, HAJIZADEH S, NÚÑEZ A, et al. Deep convolutional neural networks for detection of rail surface defects [C]//2016 International Joint Conference on Neural Networks (IJCNN). Vancouver: IEEE, 2016: 2584-2589. doi: 10.1109/ijcnn.2016.7727522http://dx.doi.org/10.1109/ijcnn.2016.7727522
GIBERT X, PATEL V M, CHELLAPPA R. Deep multitask learning for railway track inspection [J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(1): 153-164. doi: 10.1109/tits.2016.2568758http://dx.doi.org/10.1109/tits.2016.2568758
MANDRIOTA C, NITTI M, ANCONA N, et al. Filter-based feature selection for rail defect detection [J]. Machine Vision and Applications, 2004, 15(4): 179-185. doi: 10.1007/s00138-004-0148-3http://dx.doi.org/10.1007/s00138-004-0148-3
LIN J, LUO S W, LI Q Y, et al. Real-time rail head surface defect detection: a geometrical approach [C]//2009 IEEE International Symposium on Industrial Electronics. Seoul: IEEE, 2009: 769-774. doi: 10.1109/isie.2009.5214088http://dx.doi.org/10.1109/isie.2009.5214088
LI Q Y, REN S W. A visual detection system for rail surface defects [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 2012, 42(6): 1531-1542. doi: 10.1109/tsmcc.2012.2198814http://dx.doi.org/10.1109/tsmcc.2012.2198814
ZUO C, QIAN J M, FENG S J, et al. Deep learning in optical metrology: a review [J]. Light: Science & Applications, 2022, 11(1): 39. doi: 10.1038/s41377-022-00714-xhttp://dx.doi.org/10.1038/s41377-022-00714-x
LIU J Y, ZHU X F, ZHOU X Y, et al. Defect detection for metal base of TO-can packaged laser diode based on improved YOLO algorithm [J]. Electronics, 2022, 11(10): 1561. doi: 10.3390/electronics11101561http://dx.doi.org/10.3390/electronics11101561
TENG S, LIU Z C, CHEN G F, et al. Concrete crack detection based on well-known feature extractor model and the YOLO_v2 network [J]. Applied Sciences, 2021, 11(2): 813. doi: 10.3390/app11020813http://dx.doi.org/10.3390/app11020813
张景博,汪日伟,刘凤连,等.高铁摩擦片表面裂纹检测方法研究[J].光电子·激光,2021,32(9):962-969.
ZHANG J B, WANG R W, LIU F L, et al. Crack detection on the friction pads of high-speed rail [J]. Journal of Optoelectronics·Laser, 2021, 32(9): 962-969.(in Chinese)
MASCI J, MEIER U, CIRESAN D, et al. Steel defect classification with max-pooling convolutional neural networks [C]//The 2012 International Joint Conference on Neural Networks (IJCNN). Brisbane: IEEE, 2012: 1-6. doi: 10.1109/ijcnn.2012.6252468http://dx.doi.org/10.1109/ijcnn.2012.6252468
GIBEN X, PATEL V M, CHELLAPPA R. Material classification and semantic segmentation of railway track images with deep convolutional neural networks [C]//2015 IEEE International Conference on Image Processing (ICIP). Quebec City: IEEE, 2015: 621-625. doi: 10.1109/icip.2015.7350873http://dx.doi.org/10.1109/icip.2015.7350873
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779-788. doi: 10.1109/cvpr.2016.91http://dx.doi.org/10.1109/cvpr.2016.91
REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6517-6525. doi: 10.1109/cvpr.2017.690http://dx.doi.org/10.1109/cvpr.2017.690
REDMON J, FARHADI A. YOLOv3: an incremental improvement [J/OL]. arXiv, 2018: 1804.02767. doi: 10.1109/cvpr.2017.690http://dx.doi.org/10.1109/cvpr.2017.690
BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection [J/OL]. arXiv, 2020: 2004.10934.
ZHU X K, LYU S C, WANG X, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios [C]//Proceedings of 2021 IEEE/CVF International Conference on Computer Vision Workshops. Montreal: IEEE, 2021: 2778-2788. doi: 10.1109/iccvw54120.2021.00312http://dx.doi.org/10.1109/iccvw54120.2021.00312
GUO S Y, LI L L, GUO T Y, et al. Research on mask-wearing detection algorithm based on improved YOLOv5 [J]. Sensors, 2022, 22(13): 4933. doi: 10.3390/s22134933http://dx.doi.org/10.3390/s22134933
WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN [C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle: IEEE, 2020: 1571-1580. doi: 10.1109/cvprw50498.2020.00203http://dx.doi.org/10.1109/cvprw50498.2020.00203
TARG S, ALMEIDA D, LYMAN K. Resnet in resnet: generalizing residual architectures [J/OL]. arXiv, 2016: 1603.08029.
LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation [C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8759-8768. doi: 10.1109/cvpr.2018.00913http://dx.doi.org/10.1109/cvpr.2018.00913
王鹏飞,黄汉明,王梦琪.改进YOLOv5的复杂道路目标检测算法[J].计算机工程与应用,2022,58(17):81-92. doi: 10.3778/j.issn.1002-8331.2205-0158http://dx.doi.org/10.3778/j.issn.1002-8331.2205-0158
WANG P F, HUANG H M, WANG M Q. Complex road target detection algorithm based on improved YOLOv5 [J]. Computer Engineering and Applications, 2022, 58(17): 81-92. (in Chinese). doi: 10.3778/j.issn.1002-8331.2205-0158http://dx.doi.org/10.3778/j.issn.1002-8331.2205-0158
LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context [C]//13th European Conference on Computer Vision. Zurich: Springer, 2014: 740-755. doi: 10.1007/978-3-319-10602-1_48http://dx.doi.org/10.1007/978-3-319-10602-1_48
HU J, SHEN L, SUN G. Squeeze-and-excitation networks [C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141. doi: 10.1109/cvpr.2018.00745http://dx.doi.org/10.1109/cvpr.2018.00745
HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design [C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13708-13717. doi: 10.1109/cvpr46437.2021.01350http://dx.doi.org/10.1109/cvpr46437.2021.01350
贺愉婷,车进,吴金蔓.基于YOLOv5和重识别的行人多目标跟踪方法[J].液晶与显示,2022,37(7):880-890. doi: 10.37188/CJLCD.2022-0025http://dx.doi.org/10.37188/CJLCD.2022-0025
HE Y T, CHE J, WU J M. Pedestrian multi-target tracking method based on YOLOv5 and person re-identification [J]. Chinese Journal of Liquid Crystals and Displays, 2022, 37(7): 880-890. (in Chinese). doi: 10.37188/CJLCD.2022-0025http://dx.doi.org/10.37188/CJLCD.2022-0025
TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection [C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 10778-10787. doi: 10.1109/cvpr42600.2020.01079http://dx.doi.org/10.1109/cvpr42600.2020.01079
李庆党,李铁林.基于改进YOLOv3算法的钢板缺陷检测[J].电子测量技术,2021,44(2):104-108. doi: 10.19651/j.cnki.emt.2005366http://dx.doi.org/10.19651/j.cnki.emt.2005366
LI Q D, LI T L. Defect detection of steel plate based on improved YOLOv3 algorithm [J]. Electronic Measurement Technology, 2021, 44(2): 104-108.(in Chinese). doi: 10.19651/j.cnki.emt.2005366http://dx.doi.org/10.19651/j.cnki.emt.2005366
吕禾丰,陆华才.基于YOLOv5算法的交通标志识别技术研究[J].电子测量与仪器学报,2021,35(10):137-144.
LV H F, LU H C. Research on traffic sign recognition technology based on YOLOv5 algorithm [J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(10): 137-144.(in Chinese)
ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression [C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence. New York: AAAI, 2020: 12993-13000. doi: 10.1609/aaai.v34i07.6999http://dx.doi.org/10.1609/aaai.v34i07.6999
ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression [J]. Neurocomputing, 2022, 506: 146-157. doi: 10.1016/j.neucom.2022.07.042http://dx.doi.org/10.1016/j.neucom.2022.07.042
0
浏览量
39
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构