基于YOLOv5-EA的交通标志识别Traffic Sign Recognition Based On YOLOv5-EA
孟繁星;于瓅;
摘要(Abstract):
针对目前的交通标志识别模型检测速度慢、精通过的问题,提出了基于YOLOv5-EA的交通标志识别算法。首先选择YOLOv5作为基础模型,根据交通标志尺寸小的特点,引入了有效通道注意力机制(Efficient Channel Attention),不仅避免降维和跨通道交互保持性能,还显著降低了模型的复杂度,提高了特征提取的能力;其次通过增加小尺度检测层,提高模型小目标检测的能力;最后在骨干网络中使用BSConv代替了正则卷积,减少了模型的参数。实验结果表明,在公开的TT100K数据集的基础上进行调整后,对改进前后的模型进行训练对比,改进后YOLOv5-EA模型的mAP为87%,较原始的YOLOv5模型提升了3.7%,训练中的损失降低了34%,能够更快速、准确的检测到交通标志。
关键词(KeyWords): YOLOv5;ECA;交通标志;BSConv;TT100K
基金项目(Foundation): 2021安徽省重点研究与开发计划项目(202104d07020010)
作者(Authors): 孟繁星;于瓅;
DOI: 10.15916/j.issn1674-3261.2022.05.005
参考文献(References):
- [1]杜影丽,贾永红,韩静敏.自然场景车载视频道路交通限速标志的检测与识别方法[J].测绘地理信息, 2018,43(2):32-34, 37.
- [2] Soetedjo A, Yamada K. An efficient algorithm for traffic sign detection[J].Journal of Advanced Computational Intelligence and Intelligent Informatics, 2006, 10(3):409-418.
- [3] Bahlmann C, Zhu Y, Ramesh V, et al. A system for traffic sign detection, tracking, and recognition using color, shape,and motion information[C]. Las Vegas:IEEE Proceedings.Intelligent Vehicles Symposium, 2005.
- [4] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Columbus:Proceedings of the IEEE conference on computer vision and pattern recognition(CVPR), 2014:580-587.
- [5] Girshick R. Fast R-CNN[C]. Santiago:2015 IEEE International Conference on Computer Vision(ICCV), 2015:1440-1448.
- [6] Ren S, He K, Girshick R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis&Machine Intelligence, 2017, 39(6):1137-1149.
- [7] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:Unified, real-time object detection[C]. Las Vegas:2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2016:779-788.
- [8] REDMON J, FARHADI A. Yolov3:An incremental improvement[EB/OL]. https://doi.org/10.48550/arXiv.1804.02767, 2018.
- [9] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4:Optimal speed and accuracy of object detection[EB/OL].https://doi.org/10.48550/arXiv.2004.10934, 2020.
- [10] REDMON J, FARHADI A. YOLO9000:better, faster,stronger[C]. Honolulu:2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2017:7263-7271.
- [11] LIU W, ANGUELOV D, ERHAN D, et al. SSD:Single shot multi box detector[C]. Amsterdam:Proceedings of the European conference on computer vision, 2016:21-37.
- [12] FU C Y, LIU W, RANGA A, et al. DSSD:Deconvolutional single shot detector[EB/OL]. https://doi.org/10.48550/ar Xiv.1701.06659, 2017.
- [13] LI Z, ZHOU F. FSSD:feature fusion single shot multibox detector[EB/OL]. https://doi.org/10.48550/arXiv. 1712.00960, 2017.
- [14] SERMANET P, EIGEN D, ZHANG X, et al. Overfeat:Integrated recognition, localization and detection using convolutional networks[EB/OL]. https://doi.org/10.48550/arXiv. 1312. 6229, 2013.
- [15] LIU J, ZHANG D. Research on Vehicle Object Detection Algorithm Based on Improved YOLOv3 Algorithm[C].Zhejiang:5th Annual International Conference on Information System and Artificial Intelligence[ISAI2020],2020.
- [16] CHOI J, CHUN D, KIM H, et al. Gaussian YOLOv3:An accurate and fast object detector using localization uncertainty for autonomous driving[C]. Seoul:2019IEEE/CVF International Conference on Computer Vision(ICCV), 2019:502-511.
- [17] YU F, CHEN H F, WANG X, et al. Bdd100k:A diverse driving dataset for heterogeneous multitask learning[C].Seattle:2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2020:2636-2645.
- [18] XUE Z X, ZHENG Y H, XIAO J, et al. Traffic sign recognition based on multi-scale convolutional neural network[J]. Computer Engineering, 2020, 46(3):261-266.
- [19] Stallkamp J, Schlipsing M, Salmen J. Man vs. computer:Benchmarking machine learning algorithms for traffic sign recognition[J]. Neural Networks, 2012(32):323-332.
- [20] MANANA M, TU C, OWOLAWI P A. Preprocessed faster RCNN for vehicle detection[C]. Plaine Magnien:2018International Conference on Intelligent and Innovative Computing Applications(ICONIC), 2018:1-4.
- [21] WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet:A new backbone that can enhance learning capability of CNN[C].Seattle:2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW), 2020:390-391.
- [22] Lin T Y, Dollar P, Girshick R, et al. Feature Pyramid Networks for Object Detection[C]. Honolulu:Proceedings of the 30 IEEE Conference on Computer Vision and Pattern Recognition, 2017:936-944.
- [23] Ghiasi G, Lin T Y, Le Q V. NAS-FPN:Learning Scalable Feature Pyramid Architecture for Object Detection[C].Long Beach:Proceedings of the 32 IEEE Conference on Computer Vision and Pattern Recognition, 2019:7029-7038.
- [24] WANG Q, Wu B, Zhu P, et al. ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C].Seattle:Proceedings of the 33 IEEE Conference on Computer Vision and Pattern Recognition, 2020:11531-11539.
- [25] HU J, Shen L, Sun G. Squeeze-and-excitation networks[C].Salt Lake City:Proceedings of the 31 IEEE Conference on Computer Vision and Pattern Recognition,2018:7132-7141.
- [26] WANG Y N, WANG X L. Remote sensing image target detection model based on attention and feature fusion[J].Laser&Optoelectronics Progress. 2021, 58(2):363-371.
- [27] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]. Salt Lake City:2018IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018:8759-8768.