改进YOLOv5的安全帽佩戴检测算法

doi:10.3778/j.issn.1002-8331.2212-0190

摘要/Abstract

摘要： 针对目前目标检测模型结构复杂、计算量大、检测准确率低等问题，提出在工业场景下基于改进型YOLOv5的安全帽佩戴算法。在主干网络引入轻量型网络ShuffleNetv2，保留Focus结构和ShuffleNetv2共同组成主干网络，降低网络的计算量和参数量；在C3模块中引入Swin Transformer Block，得到C3STB模块，替换Neck部分原有的C3模块；设计了CBAM_H注意力机制，并将其嵌入Neck网络中，获取全局上下文信息，提高模型检测准确率。自建数据集并进行实验，实验结果表明，改进后的YOLOv5模型的参数量由6.14×106压缩到8.9×105，计算量由1.64×1010压缩到6.2×109，mAP由0.899上升到0.908，优于原模型性能。

关键词: YOLOv5, ShuffleNetv2, CBAM注意力机制, Swin Transformer Block

Abstract: Aiming at the problems of complex structure, large computation and low detection accuracy of the current target detection model, the helmet wearing algorithm based on the improved YOLOv5 is proposed in industrial scenarios. Firstly, the light-weight network ShuffleNetv2 is introduced in the backbone network, and the Focus structure and ShuffleNetv2 are retained to jointly form the backbone network to reduce the computation and number of parameters of the network; secondly, the Swin Transformer Block is made to be introduced in the C3 module to obtain the C3STB module, replacing the original C3 module in the Neck part; finally, the CBAM_ H attention mechanism is designed and embedded in the Neck network to obtain global context information and improve the model detection accuracy. The experimental results show that the improved YOLOv5 model compresses the number of parameters from 6.14×106 to 8.9×105, the computational volume from 1.64×1010 to 6.2×109, and the mAP from 0. 899 to 0. 908, which is better than the performance of the original model.

Key words: YOLOv5, ShuffleNetv2, CBAM attention mechanism, Swin Transformer Block

乔炎, 甄彤, 李智慧. 改进YOLOv5的安全帽佩戴检测算法[J]. 计算机工程与应用, 2023, 59(11): 203-211.

QIAO Yan, ZHEN Tong, LI Zhihui. Improved Helmet Wear Detection Algorithm for YOLOv5[J]. Computer Engineering and Applications, 2023, 59(11): 203-211.

参考文献

[1] 何丽，张红艳，房婉琳.融合多尺度边界特征的显著实例分割[J].计算机科学与探索，2022，16（8）：1865-1876.
HE L，ZHANG H Y，FANG W L.Salient instance segmentation via multiscale boundary characteristic network[J].Journal of Frontiers of Computer Science and Technology，2022，16（8）：1865-1876.
[2] 余震，何留杰，王振飞.基于中智理论与方向α-均值的图像边缘检测算法[J].电子测量与仪器学报，2020，34（3）：43-50.
YU Z，HE L J，WANG Z F.Image edge detection based on intelligence theory and direction α-mean[J].Journal of Electronic Measurement and Instrumentation，2020，34（3）：43-50.
[3] RUI L，YU Z H，MO D.An improved Faster-RCNN algorithm for object detection in remote sensing images[C]//Technical Committee on Control Theory，2020.
[4] LI L，HASSAN M A，YANG S，et al.Development of image-based wheat spike counter through a Faster R-CNN algorithm and application for genetic studies[J].The Crop Journal，2022，10（5）：1303-1311.
[5] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems，2015.
[6] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[J].arXiv：1512.02325，2015.
[7] SHI Q X，LI C S，GUO B Q，et al.Manipulator-based autonomous inspections at road checkpoints：application of faster YOLO for detecting large objects[J].Defence Technology，2022，18（6）：937-951.
[8] 杜晓刚，王玉琪，晏润冰，等.基于YOLO-ST的安全帽佩戴精确检测算法[J].陕西科技大学学报，2022，40（6）：177-183.
DU X G，WANG Y Q，YAN R B，et al.Accurate helmet wearing detection algorithm based on YOLO-ST[J].Journal of Shaanxi University of Science &Technology，2022，40（6）：177-183.
[9] SHEN J，XIONG X，LI Y，et al.Detecting safety helmet wearing on construction sites with bounding-box regression and deep transfer learning[J].Computer-Aided Civil and Infrastructure Engineering，2020，36（2）：180-196.
[10] WU J，CAI N，CHEN W，et al.Automatic detection of hardhats worn by construction personnel：a deep learning approach and benchmark dataset[J].Automation in Construction，2019，106：102894.
[11] MA N，ZHANG X，ZHENG H T，et al.ShuffleNet V2：practical guidelines for efficient CNN architecture design[J].arXiv：1807.11164，2018.
[12] XI D，QIN Y，WANG S.YDRSNet：an integrated YOLOv5-Deeplabv3+real-time segmentation network for gear pitting measurement[J].Journal of Intelligent Manufacturing，2023，34：1585-1599.
[13] ZHAO B Y，WU Y F，GUAN X R，et al.An improved aggregated-mosaic method for the sparse object detection of remote sensing imagery[J].Remote Sensing，2021，13（13）：2602-2602.
[14] 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.
[15] 吕晓玲，杨胜月，张明路，等.改进YOLOv5网络的鱼眼图像目标检测算法[J].计算机工程与应用，2023，59（6）：241-250.
LYU X L，YANG S Y，ZHANG M L，et al.Improved fisheye image target detection algorithm based on YOLOv5 network[J].Computer Engineering and Applications，2023，59（6）：241-250.
[16] YANG S H.Scene changes understanding framework based on graph convolutional networks and swin transformer blocks for monitoring LCLU using high-resolution remote sensing images[J].Remote Sensing，2022，14（15）：3709-3709.
[17] ZHANG P，LI D.CBAM+ASFF-YOLOXs：an improved YOLOXs for guiding agronomic operation based on the identification of key growth stages of lettuce[J].Computers and Electronics in Agriculture，2022，203：107491.
[18] HOWARD A，SANDLER M，CHU G，et al.Searching for MobileNetV3[J].arXiv：1905.02244，2019.
[19] 朱炳宇，刘朕，张景祥.融合Grad-CAM和卷积神经网络的COVID-19检测算法[J].计算机科学与探索，2022，16（9）：2108-2120.
ZHU B Y，LIU Z，ZHANG J X.COVID-19 detection algorithm combining Grad-CAM and convolutional neural network[J].Journal of Frontiers of Computer Science and Technology，2022，16（9）：2108-2120.
[20] DONIYORJON M，MADINAKHON R，SHAKHNOZA M，et al.An improved method of polyp detection using custom YOLOv4-Tiny[J].Applied Sciences，2022，12（21）：10856.
[21] XIE H，JIANG X Q，ZHANG J，et al.Lightweight and anchor-free frame detection strategy based on improved CenterNet for multiscale ships in SAR images[J].Frontiers in Computer Science，2022，4.