安全帽与反光衣的轻量化检测：改进YOLOv5s的算法

doi:10.3778/j.issn.1002-8331.2303-0458

摘要/Abstract

摘要： 安全帽与反光衣检测对生产与交通环境的安全管理具有重要意义。针对目前安全帽和反光衣检测算法参数量大、计算量大和模型体积较大等问题，提出了一种基于YOLOv5s轻量化改进的检测算法。引入GhostNet 网络结构中的Ghost模块代替原有的部分卷积与C3模块，大大降低了模型的复杂度。在主干网中增加CA注意力机制，抑制无效信息，增强对特征丰富区域的提取。用C3CBAM代替neck层的C3模块，既减少参数量，又提高了检测精度。实验结果表明，改进模型的mAP（平均精度）为93.6%，参数量为4.28×106，计算量为9.2?GFLOPs，模型大小为8.58?MB。与YOLOv5模型相比较参数量减少了39%，计算量减少了41.7%，模型大小降低37.3%。该检测算法既保证了检测的识别准确率，又实现了检测算法的轻量化。

关键词: 目标检测, YOLOv5s, GhostNet, 注意力机制, 轻量化

Abstract: Safety helmet and reflective clothing testing is of great significance to the safety management of production and traffic environment. Aiming at the problems such as large number of parameters, large amount of computation and large model size, an improved detection algorithm based on YOLOv5s is proposed in this paper. Firstly, Ghost module in GhostNet network structure is introduced to replace the original partial convolution and C3 module, which greatly reduces the complexity of the model. Then, CA attention mechanism is added to the backbone network to suppress invalid information and enhance the extraction of feature-rich regions. Finally, the C3 module of neck layer is replaced by C3CBAM, which not only reduces the number of parameters, but also improves the detection accuracy. The experimental results show that the mAP (average accuracy) of the improved model is 93.6%, the number of parameters is 4.28×106, the calculation amount is 9.2 GFLOPs, and the model size is 8.58 MB. Compared with the YOLOv5 model, the number of parameters is reduced by 39%, the amount of calculation is reduced by 41.7%, and the model size is reduced by 37.3%. The detection algorithm not only guarantees the recognition accuracy of the detection, but also realizes the lightweight of the detection algorithm.

Key words: object detection, YOLOv5s, GhostNet, attention mechanism, lightweight

张学立, 贾新春, 王美刚, 智瀚宇. 安全帽与反光衣的轻量化检测：改进YOLOv5s的算法[J]. 计算机工程与应用, 2024, 60(1): 104-109.

ZHANG Xueli, JIA Xinchun, WANG Meigang, ZHI Hanyu. Lightweight Detection of Helmets and Reflective Clothings: Improved YOLOv5s Algorithm[J]. Computer Engineering and Applications, 2024, 60(1): 104-109.

参考文献

[1] LI, Y, HAN W, ZHENG H, et al. Deep learning-based safety helmet detection in engineering management based on convolutional neural networks[J]. Advances in Civil Engineering, 2020, 2020: 1-10.
[2] JIAO L C, ZHANG F, LIU F, et al. A survey of deep learning-based object detection[J]. IEEE Access, 2019, 7: 128837-128868.
[3] 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, Venice, 2017: 2980-2988.
[4] 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, Las Vegas, 2016: 779-788.
[5] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 2017: 6517-6525.
[6] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[7] BOCHKOVSKIY A, WANG C, LIAO H M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[8] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the European Conference on Computer Vision, 2016: 21-37.
[9] 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, Columbus, 2014: 580-587.
[10] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, Santiago, 2015: 1440-1448.
[11] 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 and Machine Intelligence, 2017, 39: 1137-1149.
[12] WANG X, NIU D, LUO P, et al. A safety helmet and protective clothing detection method based on improved-Yolo V 3[C]//Proceedings of the Chinese Automation Congress, Shanghai, 2020: 5437-5441.
[13] SONG H, ZHANG X, SONG J, et al. Detection and tracking of safety helmet based on DeepSort and YOLOv5[J]. Multimedia Tools and Applications, 2023, 82(7): 10781-10794.
[14] JIN Z, QU P Q, SUN C, et al. DWCA-YOLOv5: an improve single shot detector for safety helmet detection[J]. Journal of Sensors, 2021, 2021: 1-12.
[15] ZHANG Y J, XIAO F S, LU Z M. Helmet wearing state detection based on improved Yolov5s[J]. Sensors, 2022, 22(24): 9843.
[16] SUN C, ZHANG S, QU P, et al. MCA-YOLOV5-Light: a faster, stronger and lighter algorithm for helmet-wearing detection[J]. Applied Sciences, 2022, 12(19): 9697.
[17] 程换新, 蒋泽芹, 程力, 等. 基于改进YOLOX-S的安全帽反光衣检测算法[J]. 电子测量技术, 2022, 45(6): 130-135.
CHENG H X, JIANG Z Q, CHENG L, et al. Helmet and reflective clothing detection algorithm based on improved YOLOX-S[J]. Electronic Measurement Technology, 2022, 45(6): 130-135.
[18] HAN K, WANG, Y, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 2020: 1577-1586.
[19] 李昂, 孙士杰, 张朝阳, 等. 改进YOLOv5s的轨道障碍物检测模型轻量化研究[J]. 计算机工程与应用, 2023, 59(4): 197-207.
LI A, SUN S J, ZHANG C Y, et al. Research on lightweight of improved YOLOv5 track obstacle detection model[J]. Computer Engineering and Applications, 2023, 59(4): 197-207.
[20] 邱天衡, 王玲, 王鹏, 等. 基于改进YOLOv5的目标检测算法研究[J]. 计算机工程与应用, 2022, 58(13): 63-73.
QIU T H, WANG L, WANG P, et al. Research on object detection algorithm based on improved YOLOv5[J]. Computer Engineering and Applications, 2022, 58(13): 63-73.
[21] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, 2020: 13708-13717.
[22] PANG L, LI B, ZHANG F, et al. A lightweight YOLOv5-MNE algorithm for SAR ship detection[J]. Sensors, 2022, 22(18): 7088.
[23] 宋晓凤, 吴云军, 刘冰冰, 等. 改进YOLOv5s算法的安全帽佩戴检测[J]. 计算机工程与应用, 2023, 59(2): 194-201.
SONG X F, WANG Y J, LIU B B, et al. Improved YOLOv5s algorithm for helmet wearing detection[J]. Computer Engineering and Applications, 2023, 59(2): 194-201.
[24] WOO S, PARK J, LEE J, et al. CBAM: convolutional block attention module[C]//European Conference on Computer Vision, 2018: 3-19.
[25] 刘宜轩, 程志江, 吴动波, 等. 基于改进YOLOv5的航空发动机叶片表面缺陷检测方法研究[J]. 激光杂志, 2023, 44(7): 57-61.
LIU Y X, CHENG Z J, WU D B, et al. Research on surface defect detection method of aero-engine blade based on improved YOLOv5[J]. Laser Journal, 2023, 44(7): 57-61.