改进YOLOv5的交通标志检测算法

doi:10.3778/j.issn.1002-8331.2211-0359

摘要/Abstract

摘要： 交通标志检测在自动驾驶、辅助驾驶等智能交通系统已得到广泛应用，其检测性能关乎到行车安全。针对现有目标检测算法对图像中尺寸小、分辨率低和特征不明显的交通标志检测效果较差的问题，提出了一种基于改进YOLOv5s的交通标志检测算法。将原算法中80×80小感受野目标检测层改为感受野更小的160×160检测层，提高网络模型对交通标志小目标的检测能力，降低小目标的漏检率；构建了注意力上下文模块（attention context module，ACM），对各分支获取不同的感受野，得到目标及其相邻区域的特征信息，并且使用注意力机制，让网络更关注于图像中的交通标志，避免受其他复杂信息的影响；加入特征融合模块（feature fusion module，FFM），过滤不同层上的无用信息，只保留对模型检测交通标志有用的信息；加入隐性知识，对检测层进行输出细化。实验结果表明，改进后的算法在CCTSDB交通标志检测数据集上召回率和平均精度达到94.7%、97.6%，相比原模型均有提升，在中远距离小目标检测下效果改善明显，同时检测速度为47.3?FPS，满足实时性要求。

关键词: 智能交通, 交通标志, 注意力上下文, 感受野扩增, 特征融合, 目标检测

Abstract: Traffic sign detection has been widely used in intelligent transportation systems such as automatic driving and assisted driving, and its detection performance is related to driving safety. Aiming at the problem that the existing object detection algorithm has poor detection effect on traffic signs with small size, low resolution and non-obvious features in the image, a traffic sign detection algorithm based on improved YOLOv5s is proposed. The 80×80 small sensing field object detection layer in the original algorithm is changed to a smaller 160×160 detection layer, which improves the detection ability of the network model for small object of traffic signs and reduces the missed detection rate of small object. The attention context module（ACM） is constructed to obtain the characteristic information of the target and its adjacent regions from different receptive fields for each branch, and the attention mechanism is used to make the network pay more attention to the traffic signs in the image and avoid being affected by other complex information. The feature fusion module（FFM） is added to filter out the useless information on different layers and retain only the useful information for the model to detect traffic signs. The tacit knowledge is added to refine the output of the detection layer. Experimental results show that the improved algorithm has a recall rate and average accuracy of 95.2% and 97.2% on the CCTSDB traffic sign detection dataset, which is improved compared with the original model, and the effect is significantly improved under medium and long-distance small object detection, and the simultaneous detection speed is 47.3 FPS to meet the real-time requirements.

Key words: intelligent transportation, traffic sign, attention context, receptive field amplification, , feature fusion, object detection

杨国亮, 杨浩, 余帅英, 王吉祥, 聂子玲. 改进YOLOv5的交通标志检测算法[J]. 计算机工程与应用, 2023, 59(10): 262-269.

YANG Guoliang, YANG Hao, YU Shuaiying, WANG Jixiang, NIE Ziling. Improved YOLOv5 Traffic Sign Detection Algorithm[J]. Computer Engineering and Applications, 2023, 59(10): 262-269.

参考文献

[1] 《中国公路学报》编辑部.中国汽车工程学术研究综述·2017[J].中国公路学报，2017，30（6）：1-197.
Editorial Board of China Journal of Highway and Transport.Review on China’s automotive engineering research progress：2017[J].China Journal of Highway and Transport，2017，30（6）：1-197.
[2] 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.
LU H F，LU C H.Research on traffic sign recognition technology based on YOLOv5 algorithm[J].Journal of Electronic Measurement and Instrumentation，2021，35（10）：137-144.
[3] 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.Review of traffic sign recognition methods[J].Computer Engineering and Applications，2020，56（10）：20-26.
[4] SHAO F，WANG X，MENG F，et al.Real-time traffic sign detection and recognition method based on simplified Gabor wavelets and CNNs[J].Sensors，2018，18（10）：3192.
[5] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems 28，2015.
[6] GóMEZ-MORENO H，MALDONADO-BASCNó S，GIL-JIMNéEZ P，et al.Goal evaluation of segmentation algorithms for traffic sign recognition[J].IEEE Transactions on Intelligent Transportation Systems，2010，11（4）：917-930.
[7] ZHANG J，HUANG M，JIN X，et al.A real-time Chinese traffic sign detection algorithm based on modified YOLOv2[J].Algorithms，2017，10（4）：127.
[8] REDMON J，FARHADI A.YOLO9000：better，faster，stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：7263-7271.
[9] ZHOU K，ZHAN Y，FU D.Learning region-based attention network for traffic sign recognition[J].Sensors，2021，21（3）：686.
[10] DING T，FENG K，LI T，et al.An improved anchor-free detection method for traffic sign detection[C]//2021 2nd International Symposium on Computer Engineering and Intelligent Communications，2021：348-351.
[11] WANG J，CHEN Y，GAO M，et al.Improved YOLOv5 network for real-time multi-scale traffic sign detection[J].arXiv：2112.08782，2021.
[12] Ultralytics.YOLOv5[EB/OL].[2022-04-10].https：//github.com/ultralytics/yolov5.
[13] ZAGORUYKO S，LERER A，LIN T Y，et al.A multipath network for object detection[J].arXiv：1604.02135，2016.
[14] NAJIBI M，SAMANGOUEI P，CHELLAPPA R，et al.SSH：single stage headless face detector[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision，2017：4875-4884.
[15] YU F，KOLTUN V，FUNKHOUSER T.Dilated residual networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：472-480.
[16] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[17] LIU S，QI L，QIN H，et al.Path aggregation network for instance segmentation[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition，2018：8759-8768.
[18] LIU S，HUANG D，WANG Y.Learning spatial fusion for single-shot object detection[J].arXiv：1911.09516，2019.
[19] XIAO J，ZHAO T，YAO Y，et al.Context augmentation and feature refinement network for tiny object detection[C]//ICRL 2022.
[20] HOU Q，ZHOU D，FENG J.Coordinate attention for efficient mobile network design[J].arXiv：2103.02907，2021.
[21] WANG C Y，YEH I H，LIAO H Y M.You only learn one representation：unified network for multiple tasks[J].arXiv：2105.04206，2021.
[22] 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，2022，12：23.