Detection and Tracking of Hard Hat Wearing Based on Deep Learning

Abstract

Abstract: In order to solve the shortcomings of traditional construction site safety management and reduce casualties caused by construction workers not wearing hard hats, a method for detecting and tracking hard hat wearing based on deep learning is proposed. Firstly, the YOLOv3 target detection network is used to realize the helmet wearing detection, and the Kalman filter and the KM algorithm are used to implement multi-target tracking and counting. The test results at a complex construction site show that the detection speed of the network model can reach 45 fps, with an average accuracy of 93%, and the accuracy and recall rates without a helmet are 97% and 95% respectively. This model basically realizes the real-time detection of the wearing condition of the helmet.

Key words: safety helmet, target detection, target tracking, YOLOv3 network, K-means++ clustering, Kalman filtering, KM algorithm

CLC Number:

QIN Jia, CAO Xue-hong, JIAO Liang-bao. Detection and Tracking of Hard Hat Wearing Based on Deep Learning[J]. Computer and Modernization, 2020, 0(06): 1-.

References

［1］刘俊明,孟卫华. 基于深度学习的单阶段目标检测算法研究综述［J/OL］. 航空兵器:1-11［2019-11-25］. http://kns.cnki.net/kcms/detail/41.1228.TJ.20191124.1632.007.html.
［2］  周慧娟,张强,刘羽,等. 基于YOLO2的地铁进站客流人脸检测方法［J］. 计算机与现代化, 2019(10):76-82.
［3］  林俊,党伟超,潘理虎,等. 基于YOLO的安全帽检测方法［J］. 计算机系统应用, 2019,28(9):174-179.
［4］  韩鹏,沈建新,江俊佳,等. 联合YOLO和Camshift的目标跟踪算法研究［J］. 计算机系统应用, 2019,28(9):271-277.
［5］  高军,朱宏辉,MURPHEY Y L. 基于YOLO和RRN的运动目标跟踪方法［J］. 计算机工程与设计, 2019,40(7):2019-2025.
［6］  王福建,张俊,卢国权,等. 基于YOLO的车辆信息检测和跟踪系统［J］. 工业控制计算机, 2018,31(7):89-91.
［7］  任宇杰,杨剑,刘方涛,等. 基于SSD和MobileNet网络的目标检测方法的研究［J］. 计算机科学与探索, 2019,13(11):1881-1893.
［8］  REDMON J, FARHADI A. YOLO9000: Better, faster, stronger［C］// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2017:1384-1392.
［9］  马永杰,宋晓凤. 基于YOLO和嵌入式系统的车流量检测［J］. 液晶与显示, 2019,34(6):613-618.
［10］王岳环,柴宏伟,杨岱翼. 改进的KCF实时目标跟踪算法［J］. 华中科技大学学报(自然科学版)， 2020（1）:32-36.
［11］胡超超,刘军,张凯,等. 基于深度学习的行人和骑行者目标检测及跟踪算法研究［J］. 汽车技术, 2019(7):19-23.
［12］李晶,黄山. 基于YOLOv3目标跟踪方法［J］. 电光与控制, 2019,26(10):87-93.
［13］刘惟锦,章毓晋. 基于Kalman滤波和边缘直方图的实时目标跟踪［J］. 清华大学学报(自然科学版), 2008(7):1104-1107.
［14］金红娇,罗时光. 基于二分图最佳匹配的图像检索方法［J］. 吉林化工学院学报, 2012,29(1):54-58.
［15］王飞,王林,张儒良,等. 基于融合FPN和Faster R-CNN的行人检测算法［J］. 数据采集与处理, 2019,34(3):530-537.
［16］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.
［17］林国平,余晓龙. 基于改进Faster R-CNN算法的车辆检测［J］. 闽南师范大学学报(自然科学版), 2019,32(1):44-50.
［18］赵琼,李宝清,李唐薇. 基于改进YOLOv3的目标检测算法［J/OL］. 激光与光电子学进展:1-16［2019-11-17］. http://kns.cnki.net/kcms/detail/31.1690.TN.20191107.1704.026.html.
［19］郭龙源,童光红,段厚裕,等. 基于YOLOv3的磁瓦表面缺陷检测算法［J］. 成都工业学院学报, 2019,22(3):25-30.
［20］刘雪奇,孙胜利. 基于YOLO网络模型的异常行为检测方法研究［J］. 电子设计工程, 2018,26(20):154-158.
［21］龚露鸣,徐美华,刘冬军,等. 基于混合高斯和HOG+SVM的行人检测模型［J］. 上海大学学报(自然科学版), 2018,24(3):341-351.
［22］王宇宁,庞智恒,袁德明. 基于YOLO算法的车辆实时检测［J］. 武汉理工大学学报, 2016,38(10):41-46.
［23］周志华. 机器学习［M］. 北京：清华大学出版社, 2015.

[1]	LIU Yunhai1, Feng Guang1, WU Xiaoting2, YANG Qun2 . Safety Helmet Wearing Detection Algorithm for Complex Construction Scenes [J]. Computer and Modernization, 2024, 0(12): 66-71.
[2]	CHEN Liang, LI Cheng, YI Wei, XIONG Wei, WANG Xiaofan, TANG Haidong. Helmet Wearing Detection in Electric Power Field Based on#br# Millimeter-wave Radar and Visual Fusion [J]. Computer and Modernization, 2024, 0(12): 100-107.
[3]	ZHANG Yu1, 2, LI Jing1, 2, MA Ming1, 2, WANG Zhongxiang1, 2, SUN Yan1, 2. YOLOLW: A Novel Lightweight Object Detection Model [J]. Computer and Modernization, 2024, 0(11): 91-98.
[4]	CHEN Kai1, LI Yiting1, 2, QUAN Huafeng1. A River Discarded Bottles Detection Method Based on Improved YOLOv8 [J]. Computer and Modernization, 2024, 0(11): 113-120.
[5]	WEI Xuecheng1, JIANG Lingyun1, LI Yan2, HE Fei2. Improved Roadside Monocular View Small Target Detection Algorithm Based on YOLOv5 [J]. Computer and Modernization, 2024, 0(10): 27-34.
[6]	ZHENG Shangpo1, CHEN Defu1, LI Jianli2, LIN Guoxian2, WANG Xingping3. Pedestrian Tracking Algorithm Based on Improved YOLOv5s and DeepSORT [J]. Computer and Modernization, 2024, 0(08): 54-58.
[7]	JIA Ziyu1, HUANG Huan1, HU Chun’ai2, DOU Lina2. Segmentation and Reconstruction of Left Atrial Fibrosis Based on MR [J]. Computer and Modernization, 2024, 0(05): 75-79.
[8]	SUN Ruiqi1, DOU Xiuchao2, LI Zhihua1, JIANG Xuemei2, SUN Yuhao1. An Improved YOLOv5-based Method for Dense Pedestrian Detection Under Complex Road Conditions [J]. Computer and Modernization, 2024, 0(05): 85-91.
[9]	LIU Yaoxin1, CHEN Renxi2, YANG Weihong1. A Moving Object Detection Algorithm Aiming at Jittery Drone Videos [J]. Computer and Modernization, 2024, 0(05): 99-103.
[10]	YANG Ke, DONG Bing, WU Yue, HAO Kuan-gong, PENG Zi-chen. Lightweight YOLOv4-based Target Detection Method for Remote Sensing Images of#br# Airport Fields [J]. Computer and Modernization, 2024, 0(02): 93-99.
[11]	LI Shi-bao, CONG Yu-jie. ZigBee Indoor Location Algorithm Based on Dynamic Modification of RSSI Parameters [J]. Computer and Modernization, 2024, 0(01): 35-40.
[12]	OU Jia-cheng, ZENG An, JIN Liang. CP-YOLOX-based Algorithm for Protein Target Detection in Cryo-electron Micrographs [J]. Computer and Modernization, 2023, 0(11): 113-119.
[13]	LI Yan-man, WANG Bi-heng, ZHAO Ling-yan. Safety Helmet Detection Based on Lightweight YOLOv5 [J]. Computer and Modernization, 2023, 0(10): 59-64.
[14]	GU Cheng-wei, DING Yong, LI Deng-hua. Personnel Safety Warning System in Industrial Plant Based on Computer Vision [J]. Computer and Modernization, 2023, 0(09): 20-26.
[15]	LIU Yu-shan, LIU Wei-kang, LIU Qing-hua, ZHE Tian-tian, WANG Jia-cheng. Pedestrian Detection Algorithm for Ship-borne Vehicles Based on YOLOX Combined#br# with DeepSort [J]. Computer and Modernization, 2023, 0(08): 60-67.