基于改进YOLOv5算法的交警手势识别  

Traffic police gesture recognition based on improved YOLOv5 algorithm

作　　者：王新 王赛 Wang Xin;Wang Sai(School of Physics&Electronic Information Engineering,Henan Polytechnic University,Jiaozuo 454000,China)

机构地区：[1]河南理工大学物理与电子信息学院,焦作454000

出　　处：《电子测量技术》2022年第2期129-134,共6页Electronic Measurement Technology

基　　金：国家重点研发计划(2016YFC0600906);国家自然科学基金(61403129)项目资助。

摘　　要：为了解决交警手势在光照不均匀、背景复杂的环境下识别精准度低以及实时性差等问题,以YOLOv5网络模型为基础,针对标准卷积层感受野范围有限的问题,将部分卷积层替换为自校准卷积,增大感受野范围;引入置换注意力模块,提高算法的特征提取能力;针对交警所处环境复杂多变的问题,将焦点损失函数替换为广义焦点损失函数,提高算法在复杂环境下目标框的表示能力。实验结果表明,改进后的算法在满足实时性的基础上对于交警手势的检测平均精度高达98.54%,相比于未改进的算法平均精度提高了3.39%,且损失函数的损失值更小。In order to solve the problems of low recognition accuracy and poor real-time performance of traffic police gestures in the environment of uneven illumination and complex background. Based on the YOLOv5 network model, part of the convolution layers are replaced by self-calibrated convolutions to increase the range of the receptive field. Shuffle attention module is introduced to improve the feature extraction ability of the algorithm. Aiming at the complex and changeable environment of traffic police, the focal loss function was replaced by generalized focal loss function to improve the expression ability of target frame in complex environment. Experimental results show that on the basis of real-time performance, the average accuracy of the improved algorithm for traffic police gesture detection is as high as 98.54%, which is 3.39% higher than that of the unimproved algorithm, and the loss value of the loss function is smaller.

关 键 词：YOLOv5 自校准卷积 SA模块 GFL函数 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]