摘要
提出一种基于改进型YOLO v5算法的安全帽佩戴检测方法,通过安全帽区域与头部区域的位置关系判断安全帽佩戴情况,对算法中候选框、卷基层、输入端和量化方法进行改进.通过与其他安全帽佩戴检测方法进行试验对比分析,改进后的算法可以提高识别精度与速度,更好满足实时监控的需求.
This paper proposes a safety helmet wearing detection method based on improved Yolo V5,which can be used to judge safety helmet wearing situation through position relationship between safety helmet area and head area,so as to improve candidate box,volume base,input and quantization method and algorithm.The improved algorithm can be used to improve the recognition accuracy and speed,and better meet the needs of real-time monitoring.Finally,the performance of other safety helmet wearing detection methods is compared and analyzed through experiments,showing that the improved algorithm can improve the accuracy and speed of detection,thus fulfilling the need of real time monitoring.
作者
朱晓春
陈子涛
ZHU Xiao-chun;CHEN Zi-tao(School of Automation, Nanjing Institute of Technology, Nanjing 211167, China)
出处
《南京工程学院学报（自然科学版）》
2021年第4期7-11,共5页
Journal of Nanjing Institute of Technology(Natural Science Edition)
