一种融合RepVGG和YOLOv5的行人检测方法  

A Pedestrian Detection Method of Integrated RepVGG and YOLOv5

作　　者：刘春雷 李志华[1,2] 王超 王连贺[1,2] 张元彪 LIU Chun-lei;LI Zhi-hua;WANG Chao;WANG Lian-he;ZHANG Yuan-biao(School of Information and Electrical Engineering,Hebei University of Engineering,Handan 056000,China;Hebei Key Laboratory of Security&Protection Information Sensing and Processing,Handan 056000,China)

机构地区：[1]河北工程大学信息与工程学院,邯郸056000 [2]河北省安防信息感知与处理重点实验室,邯郸056000

出　　处：《科学技术与工程》2023年第7期2945-2951,共7页Science Technology and Engineering

基　　金：邯郸市科技研发计划(21422031251)。

摘　　要：现如今,基于YOLOv5的网络模型被广泛应用在行人检测的任务中,在精度和速度上有着良好的效果。但在终端设备上部署使用,往往受到算力的限制。因而,基于RepVGG模型改进的主干网络,并且为了提高在密集人群和复杂环境下的适应性,加入了坐标注意力机制,扩大感受野的同时增强感兴趣区域的权重。经过实验测试,这种轻量化的网络参数量和计算量比较小,而且检测精度和鲁棒性也比较高,能够在一定程度下满足工程应用的要求。Nowadays,the detection model based on YOLOv5 network are widely used in the task of pedestrian detection,and have good results in terms of accuracy and speed.However,it is often limited by computing power on terminal devices.Therefore,based on the improved backbone network of the RepVGG model,in order to improve the adaptability in dense crowds and complex environments,a coordinate attention mechanism was introduced to expand the receptive field and enhance the weight of the region of interest.After experimental testing,this lightweight network parameter and calculation amount is relatively small,and the detection accuracy and robustness are relatively high,which can meet the requirements of engineering applications to a certain extent.

关 键 词：行人检测 RepVGG 注意力机制 YOLOv5 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]