Lightweight Helmet Wearing Detection Algorithm of Improved YOLOv5

doi:10.3778/j.issn.1002-8331.2111-0346

Abstract

Abstract: Aiming at the problems of the existing helmet wearing detection algorithm, such as multiple parameters, complex network, large amount of calculation, which is not suitable for deployment on embedded devices, and poor discrimination of occlusion targets, an improved lightweight helmet detection algorithm, YOLo-M3, is proposed.?Firstly, the YOLOv5s backbone network is replaced by MobileNetV3 for feature extraction, which reduces the number of parameters and computation of the network.?Secondly, Diou-NMS is used to replace NMS to improve the identification of occlusion targets. CBAM attention mechanism is added to make the model pay more attention to the main information to improve the detection accuracy. Finally, knowledge distillation is carried out to increase the recall rate and accuracy of model detection.?Experiments verify that YOLO-M3 algorithm can improve the identification of occlusion targets, and reduce the calculation amount of YOLOv5s model by 42% and the model size by 40% while ensuring a high average detection accuracy, thus reducing the hardware cost and meeting the requirements of deployment in embedded end.

Key words: lightweight, object detection, improved YOLOv5, attentional mechanism, knowledge of distillation

摘要： 针对现有的对安全帽佩戴检测算法的参数多、网络复杂、计算量大、不利于在嵌入式等设备进行部署，且对遮挡目标辨别度差等问题，提出了一种改进的轻量级的安全帽检测算法YOLO-M3，先将YOLOv5s主干网络替换为MobileNetV3来进行特征提取，降低了网络的参数量和计算量。使用DIoU-NMS替换NMS，提高对遮挡目标的辨识度，添加CBAM注意力机制使模型更关注主要信息以提升检测精度，对模型进行知识蒸馏，增加模型检测的召回率和准确度。通过实验验证了YOLO-M3算法提高了对遮挡目标的辨识度，在保证较高的检测平均精度时，将YOLOv5s模型的计算量降低了42%，模型大小降低了40%，降低了硬件成本，满足在嵌入式端部署的需求。

关键词: 轻量化, 目标检测, 改进YOLOv5, 注意力机制, 知识蒸馏

YANG Yongbo, LI Dong. Lightweight Helmet Wearing Detection Algorithm of Improved YOLOv5[J]. Computer Engineering and Applications, 2022, 58(9): 201-207.

杨永波, 李栋. 改进YOLOv5的轻量级安全帽佩戴检测算法[J]. 计算机工程与应用, 2022, 58(9): 201-207.

References

[1] 张仕廉，王黎明，叶贵，等.建筑安全全要素投入研究：以重庆市为例[J].中国安全科学学报，2018，28（3）：161-166.
ZHANG S L，WANG L M，YE G，et al.Research on total factor investment in construction safety：a case study in Chongqing[J].China Safety Science Journal，2018，28（3）：161-166.
[2] 施辉，陈先桥，杨英.改进YOLOv3的安全帽佩戴检测方法[J].计算机工程与应用，2019，55（11）：213-220.
SHI H，CHEN X Q，YANG Y.Safety helmet wearing detection method of improved YOLO v3[J].Computer Engineering and Applications，2019，55（11）：213-220.
[3] 肖体刚，蔡乐才，高祥，等.改进YOLOv3的安全帽佩戴检测方法[J].计算机工程与应用，2021，57（12）：216-223.
XIAO T G，CAI L C，GAO X，et al.Improved YOLOv3 helmet wearing detection method[J].Computer Engineering and Applications，2021，57（12）：216-223.
[4] 张锦，屈佩琪，孙程，等.基于改进YOLOv5的安全帽佩戴检测方法[J/OL].计算机应用：1-11[2021-11-10].http：//kns.cnki.net/kcms/detail/51.1307.TP.20210908.1727.002.html.
ZHANG J，QU P Q，SUN C，et al.Safety helmet wearing detection method based on improved YOLOv5[J/OL].Journal of Computer Applications：1-11[2021-11-10].http：//kns.cnki.net/kcms/detail/51.1307.TP.20210908.1727.002.html.
[5] HOWARD A，SANDLER M，CHEN B，et al.Searching for MobileNetV3[C]//2019 IEEE/CVF International Conference on Computer Vision（ICCV），2019：1314-1324.
[6] LI Y G，WEI H，HAN Z，et al.Deep learning-based safety helmet detection in engineering management based on convolutional neural networks[J].Advances in Civil Engineering，2020（6）：1-10.
[7] WANG W，LI Y T，ZOU T，et al.A novel image classifi-cation approach via dense-mobilenet models[J].Mobile Information Systems，2020：1-8.
[8] SANDLER M，HOWARD A，ZHU M，et al.MobileNetV2：inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：4510-4520.
[9] TAN M X，CHEN B，PANG R M，et al.MnasNet：platform-aware neural architecture search for mobile[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2019：2815-2823.
[10] RAMACHANDRAN P，ZOPH B，LE Q V.Searching for activation functions[C]//6th International Conference on Learning Representations，2018.
[11] WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module[C]//Proceedings of the 2018 European Conference on Computer Vision.Cham：Springer，2018：3-19.
[12] GONG M，WANG D，ZHAO X，et al.A review of non-maximum suppression algorithms for deep learning target detection[C]//Seventh Symposium on Novel Photoelectronic Detection Technology and Application，2021.
[13] GOU J P，YU B S，MAYBANK S J，et al.Knowledge distillation：a survey[J].International Journal of Computer Vision，2021，129（6）：1789-1819.
[14] PENG D，SUN Z，CHEN Z，et al.Detecting heads using feature refine net and cascaded multi-scale archi-tecture[C]//Proceedings of the 2018 International Conference on Pattern Recognition.Piscataway：IEEE，2018.
[15] 蒋润熙，阿里甫·库尔班，耿丽婷.面向轻量化网络的安全帽检测算法[J].计算机工程与应用，2021，57（20）：263-270.
JIANG R X，ALIFU·KUERBAN，GENG L T.Safety helmet detection algorithm for lightweight network[J].Computer Engineering and Applications，2021，57（20）：263-270.