改进YOLOv5的交通标志检测方法

doi:10.3778/j.issn.1002-8331.2302-0163

摘要/Abstract

摘要： 交通标志检测对自动驾驶和车辆安全具有重要意义，但交通标志受光照影响尺度变化较大，存在遮挡等情况导致模型检测精度较低，有误检、漏检等问题。基于YOLOv5目标检测算法，提出了一种改进的交通标志检测方法。该方法引入递归门控卷积、SOCA注意力机制和回归损失函数，在TT100K和CCTSDB数据集上进行了大量实验。实验结果表明，改进的YOLOv5在TT100K数据集上平均准确率（mAP）提高了43.7个百分点，mAP@0.5：0.95提高了34.6个百分点，在CCTSDB数据集上平均准确率（mAP）提高了2个百分点，mAP@0.5：0.95提高了1个百分点。

关键词: 交通标志检测, 递归门控卷积, 注意力机制, 回归损失函数

Abstract: Traffic sign detection is of great significance to autonomous driving and vehicle safety, but the scale of traffic signs is affected by illumination and changes greatly, and there are occlusion situations, resulting in low model detection accuracy, false detection, missed detection and other problems. In this paper, a new traffic sign detection method is proposed by improving the YOLOv5 object detection algorithm. This method introduces recursive gated convolution, SOCA attention mechanism and regression loss function, and a large number of experiments are carried out on TT100K and CCTSDB datasets. The experimental results show that the improved YOLOv5 has an average accuracy（mAP） increase of by 43.7?percentage points on the TT100K dataset, 34.6 percentage points on the mAP@0.5：0.95, 2 percentage points on the CCTSDB dataset, and 1 percentage point on the mAP@0.5：0.95.

Key words: traffic sign detection, recursive gated convolution, attention mechanism, regression loss function

韦强, 胡晓阳, 赵虹鑫. 改进YOLOv5的交通标志检测方法[J]. 计算机工程与应用, 2023, 59(13): 229-237.

WEI Qiang, HU Xiaoyang, ZHAO Hongxin. Improved Traffic Sign Detection Method for YOLOv5[J]. Computer Engineering and Applications, 2023, 59(13): 229-237.

参考文献

[1] 伍晓晖，田启川.交通标志识别方法综述[J].计算机工程与应用，2020，56（10）：20-26.
WU X H，TIAN Q C.Survey of traffic sign recognition[J].Computer Engineering and Applications，2020，56（10）：20-26.
[2] 黄刚.基于深度学习的城市交通场景目标检测算法研究[D].杭州：浙江工商大学，2018.
HUANG G.The study of object detection methods via deep learning in urban transportation[D].Hanghzou：Zhejiang Gongshang University，2018.
[3] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision，Amsterdam，The Netherlands，October 11-14，2016：21-37.
[4] LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2980-2988.
[5] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[6] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[7] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[8] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[9] TIAN Z，SHEN C，CHEN H，et al.FCOS：fully convolutional one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9627-9636.
[10] ZHANG J，ZOU X，KUANG L D，et al.CCTSDB 2021：a more comprehensive traffic sign detection benchmark[J].Human-centric Computing and Information Sciences，2022，12.
[11] ZHU Z，LIANG D，ZHANG S，et al.Traffic-sign detection and classification in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：2110-2118.
[12] STALLKAMP J，SCHLIPSING M，SALMEN J，et al.The German traffic sign recognition benchmark：a multi-class classification competition[C]//Proceedings of the 2011 International Joint Conference on Neural Network，2011：1453-1460.
[13] 郭璠，张泳祥，唐琎，等.YOLOv3-A：基于注意力机制的交通标志检测网络[J].通信学报，2021，42（1）：87-99.
GUO F，ZHANG Y X，TANG J，et al.YOLOv3-A：a traffic sign detection network based on attention mechanism[J].Journal on Communications，2021，42（1）：87-99.
[14] 王泽华.改进YOLOv4在道路交通标志识别的应用研究[D].邯郸：河北工程大学，2021.
WANG Z H.Based on the application of improving YOLOv4 algorithm in road traffic sign recognition[D].Handan：Hebei University of Engineering，2021.
[15] 胡昭华，王莹.改进YOLOv5的交通标志检测算法[J].计算机工程与应用，2023，59（1）：82-91.
HU Z H，WANG Y.Improved traffic sign detection algorithm for YOLOv5[J].Computer Engineering and Applications，2023，59（1）：82-91.
[16] 杨晓玲，江伟欣，袁浩然.基于YOLOv5的交通标志识别检测[J].信息技术与信息化，2021（4）：28-30.
YANG X L，JIANG W X，YUAN H R.Traffic sign recognition detection based on YOLOv5[J].Information Technology and Informatization，2021（4）：28-30.
[17] 胡均平，王鸿树，戴小标，等.改进YOLOv5的小目标交通标志实时检测算法[J].计算机工程与应用，2023，59（2）：185-193.
HU J P，WANG H S，DAI X B，et al.Real-time detection algorithm for small-target traffic signs based on improved YOLOv5[J].Computer Engineering and Applications，2023，59（2）：185-193.
[18] 张上，王恒涛，冉秀康.基于YOLOv5的轻量化交通标志检测方法[J].电子测量技术，2022，45（8）：129-135.
ZHANG S，WANG H T，RAN X K.Lightweight traffic sign detection algorithm based on YOLOv5[J].Electronic Measurement Technology，2022，45（8）：129-135.
[19] RAO Y，ZHAO W，TANG Y，et al.Hornet：efficient high-order spatial interactions with recursive gated convolutions[J].arXiv：2207.14284，2022.
[20] FRANK E，HALL M.A simple approach to ordinal classification[C]//Proceedings of the European Conference on Machine Learning，2001：145-156.
[21] ZHANG Y F，REN W，ZHANG Z，et al.Focal and efficient IOU loss for accurate bounding box regression[J].Neurocomputing，2022，506：146-157.
[22] 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.
[23] LI H，XIONG P，AN J，et al.Pyramid attention network for semantic segmentation[J].arXiv：1805.10180，2018.