Improved YOLOv5 Algorithm for Real-Time Detection of Irregular Driving Behavior

doi:10.3778/j.issn.1002-8331.2211-0188

Abstract

Abstract: Aiming at the problems of existing irregular driving behavior detection algorithms, such as occupying too much memory, large amount of calculation, being difficult to deploy on edge devices and interfering with detection targets in dim conditions, a lightweight irregular driving behavior real-time detection algorithm with improved YOLOv5 model is proposed. Firstly, the SE attention mechanism is introduced in the Backbone network of the YOLOv5 model, and then the CSP module of the Backbone network is replaced by a lightweight GhostBottleNeck network module, which tends to reduce the number of model references. Next, the activation function in the original network is modified into SiLU function, which can improve the accuracy of model detection and enhance the robustness of the model. Finally, the improved model and the original network are tested to verify the effectiveness and real-time performance of the modified method. Experimental results show that the improved YOLOv5-GS algorithm can improve the detection accuracy of irregular driving behavior, the number of parameters is reduced by 20.75%, the detection speed is increased by 75%, and the required hardware cost is greatly reduced, which is suitable for deployment on small edge equipment.

Key words: non-standard driving behavior detection, lightweight, attention mechanism, YOLOv5, GhostBottleNeck

摘要： 针对现有的不规范驾驶行为检测算法占用内存多、计算量大、难以在边缘设备部署且在昏暗条件下对检测目标有干扰等问题，提出了一种改进YOLOv5模型的轻量级不规范驾驶行为实时检测算法。将SE注意力机制引入到YOLOv5模型的Backbone网络部分，再将Backbone网络里的CSP模块替换为轻量化的GhostBottleNeck网络模块，从而减少模型的参数量；将原网络中的激活函数改进成SiLU函数，可提高模型检测的准确率，增强模型的鲁棒性；对改进的模型以及原网络进行相关的测试，验证所修改方法的有效性以及实时性。实验结果表明，改进后的YOLOv5-GS算法提高了对不规范驾驶行为的检测精度，参数量降低20.75%，检测速度提升75%，极大地降低了所需的硬件成本，适用于在小型边缘设备上部署。

关键词: 不规范驾驶行为检测, 轻量化, 注意力机制, YOLOv5, GhostBottleNeck

ZOU Peng, YANG Kaijun, LIANG Chen. Improved YOLOv5 Algorithm for Real-Time Detection of Irregular Driving Behavior[J]. Computer Engineering and Applications, 2023, 59(13): 186-193.

邹鹏, 杨凯军, 梁晨. 改进YOLOv5的轻量级不规范驾驶行为实时检测[J]. 计算机工程与应用, 2023, 59(13): 186-193.

References

[1] 贺宜，杨鑫炜，吴兵，等.中美交通事故数据统计方法比较研究[J].交通信息与安全，2018，36（1）：19-27.
HE Y，YANG X W，W B，et al.A comparison of statistical survey metheds of traffic accident data between China and the Uuited States[J].Journal of Transport Information and Safety，2018，36（1）：19-27.
[2] 李光东，程进，周子肖，等.基于深度学习的不规范驾驶行为智能识别系统[J].传感器世界，2020，26（2）：7-11.
LI G D，CHENG J，ZHOU Z X，et al.Irregular driving behavior intelligent recognition system based on deep learning[J].Sensor World，2020，26（2）：7-11.
[3] 张志威.基于机器视觉的异常驾驶行为检测方法研究[D].长沙：湖南大学，2020.
ZHANG Z W.Research on abnormal driving behavior detection method based on machine vision[D].Changsha：Hunan University，2020.
[4] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the International Conference on Learning Representations，2015：1-14.
[5] YAN S Y，TENG Y X，JEREMY S，et al.Driver behavior recognition based on deep convolutional neural networks[C]//Proceedings of the 12th International Conference on Natural Computation，Fuzzy Systems and Knowledge Discovery，2016：636-641.
[6] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：580-587.
[7] 田文洪，曾柯铭，莫中勤，等.基于卷积神经网络的驾驶员不安全行为识别[J].电子科技大学学报，2019，48（3）：381-387.
TIAN W H，ZENG K M，MO Z Q，et al.Recognition of unsafe driving behaviors based on convolutional neural network[J].Journal of University of Electronic Science and Technology of China，2019，48（3）：381-387.
[8] 王丹.基于机器视觉的驾驶员打电话行为检测[D].北京：北京理工大学，2015.
WANG D.Driver phone call behavior detection based on machine vision[D].Beijing：Beijing Institute of Technology，2015.
[9] LE T H N，ZHENG Y T，ZHU C C，et al.Multiple scale faster-renn approach to driver’s cell-phone usage and hands on steering wheel detection[C]//Proceedings of the Computer Vision and Pattern Recognition Workshops，2016：46-53.
[10] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards realtime object detection with region proposal networks[C]//Proceedings of International Conference on Neural Information Processing Systems，2015：91-99.
[11] SESHADRI K，JUEFEIXU F，PAL D K，et al.Driver cell phone usage detection on strategic highway research program（SHRP2）face view videos[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops，2015：35-43.
[12] OHN-BAR E，MARTIN S，TAWARI A，et al.Head，eye，and hand pattems for driver activity recognition[C]//Proceedings of the Intemational Conference on Pattern Recognition，2014.
[13] 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，2016：6517-6525.
[14] REDMON J，FARHADI A.YOL09000：better，faster，stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017.
[15] REDMON J，FARHADI A.YOLOv3：an incremental improvement[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018.
[16] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2020.
[17] 殷远齐，徐源，邢远新.基于YOLO v4的车辆目标检测算法[J].计算机与现代化，2022（7）：8-14.
YIN Y Q，XU Y，XING Y X.Vehicle target detection algorithm based on YOLO v4[J].Computer and Modernization，2022（7）：8-14.
[18] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[J].arXiv：1807.06521，2018.
[19] 王新宇.基于YOLOv5目标检测算法的交通信号灯智能控制装置设计[J].公路交通技术，2022，38（1）：142-148.
WANG X Y.Design of intelligent control device of traffic signal light based on YOLOv5 object detection algorithm[J].Technology of Highway and Transport，2002，38（1）：142-148.
[20] 邓天民，谭思奇，蒲龙忠.基于改进YOLOv5s的交通信号灯识别方法[J].计算机工程，2022，48（9）：55-62.
DENG T M，TAN S Q，PU L Z.Traffic signal recognition method based on improved YOLOv5s[J].Computer Engineering，2022，48（9）：55-62.
[21] 牛洪超，胡晓兵，罗耀俊.基于M-YOLO的自动驾驶下目标识别算法[J].计算机工程与设计，2022，43（8）：2213-2220.
NIU H C，HU X B，LUO Y J.Target recognition algorithm in autonomous driving based on M-YOLO[J].Computer Engineering and Design，2022，43（8）：2213-2220.
[22] 田坤，李冠，赵卫东.基于YOLO和极限学习机的驾驶员安全带检测模型研究[J].计算机应用与软件，2019，36（11）：196-201.
TIAN K，LI G，ZHAO W D.Driver’s seatbelt detection based on YOLO and extreme learning machine[J].Computer Applications and Software，2019，36（11）：196-201.
[23] 汤科元，刘川莉，蔡乐才，等.基于YOLO轻量化网络的交通标志检测算法[J].四川轻化工大学学报（自然科学版），2021，34（5）：62-70.
TANG K Y，LIU C L，CAI L C，et al.Traffic sign detection algorithm based on YOLO lightweight network[J].Journal of Sichuan University of Science & Engineering（Natural Science Edition），2021，34（5）：62-70.
[24] HAN K，WANG Y，TIAN Q，et al.GhostNet：more features from cheap operations[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2020：1577-1586.
[25] ZHANG H B，XIONG Q P，JIANG Z L，et al.Joint SENet heterogeneous layer feature fusion and integrated learning for material image recognition[J].Control and Decision，2021（6）.
[26] 朱张莉，饶元，吴渊，等.注意力机制在深度学习中的研究进展[J].中文信息学报，2019，33（6）：11.
ZHU Z L，RAO Y，WU Y，et al.Research progress of attention mechanism in deep learning[J].Journal of Chinese Information Processing，2019，33（6）：11.
[27] 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.
[28] HE K，ZHANG X，REN S，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（9）：1904-1916.
[29] 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，2018：8759-8768.
[30] 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.
[31] ZHENG Z H，WANG P，LIU W，et al.Distance-IoU loss：faster and better learning for bounding box regression[C]//Proceedings of AAAI Conference on Artificial Intelligence，2020：12993-13000.