[1]顿伟超,王淑青,张鹏飞,等. 基于改进YOLOv4的电力高空作业安全带检测[J].湖北工业大学学报,2022,(5):6-11.
　DUN Weichao,WANG Shuqing,ZHANG Pengfei,et al. Safety Belt Detection Algorithm for Electric Aerial Work Based on Improved YOLOv4[J].,2022,(5):6-11.
点击复制

 基于改进YOLOv4的电力高空作业安全带检测()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2022年第5期
页码:
6-11
栏目:
湖北工业大学学报
出版日期:
2022-10-25

文章信息/Info

Title:
 Safety Belt Detection Algorithm for Electric Aerial Work Based on Improved YOLOv4
文章编号:
1003-4684(2022)05-0006-06
作者:
 顿伟超;  王淑青;  张鹏飞;  王 娟
 湖北工业大学电气与电子工程学院， 湖北 武汉 430068
Author(s):
 DUN Weichao; WANG Shuqing ; ZHANG Pengfei; WANG Juan
 School of Electrical and Electronic Engin., Hubei Univ. of Tech., Wuhan 430068，China
关键词:
 ; 安全带;  深度学习;  YOLOv4;  MobileNet;  卷积神经网络
Keywords:
 ; safety belt;  deep learning;  YOLOv4;  MobileNet;  convolutional neural network
分类号:
TP391.4
文献标志码:
A
摘要:
 为了让电力工作人员在电力作业中采取规范的防护措施，提出了一种基于改进YOLOv4的电力高空作业识别及安全带佩戴检测算法。首先，该算法采用MobileNetv2作为主干提取网络，在保证较好的特征提取效果同时降低了网络的参数量，提高模型的识别速度；然后使用K-means聚类算法对数据集中的目标边框重新聚类，并调整空间金字塔池化结构，提高模型的检测精度；最后使用Soft-NMS算法替换原NMS算法降低目标的漏检率。实验结果表明，改进YOLOv4网络模型比原YOLOv4模型mAP提高3.2%，检测速度提高30fps，模型的训练权重大小压缩4.16倍，算法在高空作业安全带检测上具有很强的实用性和高效性。
Abstract:
 Power aerial work accidents occur frequently. In order to allow electric power workers to take standardized protective measures during electric power operations, this paper proposes a recognition algorithm for power high-altitude operation and safety belt wearing based on improved YOLOv4. Firstly, this algorithm uses MobileNetv2 as the backbone extraction network, which reduces the amount of network parameters and improves the recognition speed of the model while ensuring a good feature extraction effect. Then we use the K-means clustering algorithm to re-cluster the target borders in the data set, and adjust the spatial pyramid pooling structure to improve the detection accuracy of the model. Finally, the Soft NMS algorithm is used to replace the original NMS algorithm to reduce the missed detection rate of the target. The experimental results show that the mean Average Precision of the improved YOLOv4 network model is 3.2% higher than the original YOLOv4 model, the detection speed is increased by 30 frames per second (fps), and the training weight of the model is reduced by 4.16 times. In conclusion, the proposed algorithm has strong practicability and high efficiency in safety belt detection of electric aerial work.

参考文献/References:

[1] REDMON J, DIVVALA S, GIRSHICK R, et al. You Only look once: unified, real time object detection[C]∥Computer Vision and Pattern Recognition， 2017, 6517-6525.
[2] REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2017, 6517-6525.
[3] REDMON J, FARHADI A. Yolov3: An incremental improvement[C]∥IEEE Conference on Computer Vision and Pattern Recognition, 2018, 1804.0276. 
[4] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection[C]∥IEEE Conference on Computer Vision and Pattern Recognition. 2020. arXiv: 2004.10934v1 [cs.CV].
[5] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]∥Proceedings of the European Conference on Computer Vision(ECCV), 2016, 21-37.
[6] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society, 2014: 580-587.
[7] GIRSHICK R. Fast R-CNN[C]∥Proceedings of the IEEE International Conference on Computer Vision, 2015, 1440-1448.
[8] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]∥Proceedings of the 2015 advances in Neural Information Processing Systems, 2015， 91-99. 
[9] He K M, Gkioxari G, Dollar P, et al. Mask R-CNN[C]∥Proceedings of the IEEE international conference on computer vision. Venice: IEEE Press, 2017, 2961-2969.
[10] 许凯, 邓超. 基于改进YOLOv3的安全帽佩戴识别算法[J]. 激光与光电子学进展, 2021, 58(6): 300-307. 
[11] 冯文文, 曹银杰, 李晓琳, 等. 基于改进的深度卷积神经网络的人脸疲劳检测[J]. 科学技术与工程, 2020, 20(14): 5680-5687.
[12] 霍星, 费志伟, 赵峰, 等. 深度学习在驾驶员安全带检测中的应用[J]. 计算机科学, 2019, 46(S1): 182-187.
[13] 谢晓方,刘厚君,张龙杰,等. 融合轻量级YOLOv4与KCF算法的红外舰船目标识别[J]. 兵器装备工程学报, 2021,42(6): 175-182.
[14] HE K M, 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.
[15] 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(CVPR), 2018,8759-8768.
[16] HOWARD A G, ZHU M, CHEN B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J/OL].[2021-11-30].arXiv preprint arXiv:1704.04861, 2017.
[17] 张陶宁, 陈恩庆, 肖文福. 一种改进MobileNet_YOLOv3网络的快速目标检测方法[J]. 小型微型计算机系, 2021, 42(5): 1008-1014.
[18] 李彬,汪诚,吴静,等. 改进YOLOv4算法的航空发动机部件表面缺陷检测[J]. 激光与光电子学进展, 2021, 58(14): 414-423.
[19] BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS-improving object detection with one line of code[C]∥2017 IEEE International Conference on Computer Vision (ICCV), August 8, 2017,5562-5570.

相似文献/References:

[1]熊韧,曹海印,王焱清,等.非牛顿润滑静压轴承的节流器流量方程修正[J].湖北工业大学学报,2019,34(5):6.
　XIONG Ren,CAO Haiyin,WANG Yanqing,et al.Modified restrictor flow equations of hydrostatic bearings ubricated by non-Newtonian fluids[J].,2019,34(5):6.
[2]王照远,曹 民,王 毅,等. 场景与数据双驱动的隧道图像拼接方法[J].湖北工业大学学报,2020,(4):11.
　WANG Zhaoyuan,CAO Min,WANG Yi,et al. Tunnel Image Stitching Method based on Scene and Data[J].,2020,(5):11.
[3]潘 健,梁佳成,陈凤娇,等. 单电流闭环多重PR控制的LCL型逆变器[J].湖北工业大学学报,2020,(4):16.
　PAN Jian,LIANG Jiacheng,CHEN Fengjiao,et al. Design of LCL Grid Connected Inverter based on Single Closed Loop Control and Multiple PR Controllers[J].,2020,(5):16.
[4]王晓光,赵 萌,文益雪,等. 定子闭口槽结构对永磁电机齿槽转矩影响分析[J].湖北工业大学学报,2020,(4):25.
　WANG Xiaoguang,ZHAO Meng,WEN Yixue,et al. Study on Cogging Torque and Vibration Noise of Permanent Magnet Motor with Segmental Stator and Closed-Slot[J].,2020,(5):25.
[5]宇 卫,凃玲英,陈 健. 风电场集中接入对集电线电流保护的影响[J].湖北工业大学学报,2020,(4):29.
　YU Wei,TU Lingying,CHEN Jian. Effect of the Collective Line Current Protection when Wind Farms are Centralized Accessed to the Power System[J].,2020,(5):29.
[6]廖政斌,王泽飞,祝 珊. 二惯量系统谐振在线抑制及相位补偿[J].湖北工业大学学报,2020,(4):34.
　LIAO Zhengbin,WANG Zefei,ZHU Shan. Online Resonance Suppression and Phase Compensation for Double Inertia System[J].,2020,(5):34.
[7]王 欣,游 颖,姜天翔,等. 面向3D打印过程的产品工艺设计和优化[J].湖北工业大学学报,2020,(4):39.
　WANG Xin,YOU Ying,JIANG Tianxiang,et al. Product Process Design and Optimization for 3D Printing Processes[J].,2020,(5):39.
[8]冉晶晶,文 红,罗雅梅,等. 全自动样品前处理平台及其控制系统[J].湖北工业大学学报,2020,(4):43.
　RAN Jingjing,WEN Hong,LUO Yamei,et al. Research on Automatic Sample Preprocessing Platform and its Control System[J].,2020,(5):43.
[9]杨 磊,马志艳,石 敏,等. 基于模糊PID的小型冷库过热度控制方法[J].湖北工业大学学报,2020,(4):43.
　YANG Lei,MA Zhiyan,SHI Min,et al. Research on Superheat Control Method of Small Cold Storage based on Fuzzy PID[J].,2020,(5):43.
[10]黄 晶,周细枝,周业望. 动态注塑成型模具的设计与实验研究[J].湖北工业大学学报,2020,(4):52.
　HUANG Jing,ZHOU Xizhi,ZHOU Yewang. Design and Experimental Study of Dynamic Injection Molding[J].,2020,(5):52.

备注/Memo

备注/Memo:
［收稿日期］ 2021-11-30
［基金项目］ 国家自然科学基金青年基金(62006073)
［第一作者］ 顿伟超（1994-），男，河南许昌人，湖北工业大学硕士研究生，研究方向为人工智能与深度学习
［通信作者］ 王淑青（1969-），女，河北衡水人，湖北工业大学教授，研究方向为人工智能
更新日期/Last Update: 2022-10-25