南京信息工程大学学报2024，Vol.16Issue(1)：11-19,9.DOI:10.13878/j.cnki.jnuist.20230502002
基于改进YOLOv5s的交通标识检测算法
Traffic sign detection based on improved YOLOv5s
李孟浩 1袁三男1
作者信息
- 1. 上海电力大学 电子与信息工程学院,上海, 201306
- 折叠
摘要
Abstract
An algorithm based on improved YOLOv5s is proposed to address the problems of small percentage of traffic signs in the image,low detection accuracy and complex surrounding environment.First,the attention mecha-nism of ECA(Efficient Channel Attention)is added to the backbone network part to enhance the feature extraction ability of the network and effectively solve the problem of complex surrounding environment.Second,the HASPP(Hybrid Atrous Spatial Pyramid Pooling)is proposed,which enhances the network's ability to combine context.Fi-nally,the neck structure in the network is modified to allow efficient fusion of high level features with underlying features while avoiding information loss across convolutional layers.Experimental results show that the improved al-gorithm achieves an average detection accuracy of 94.4%,a recall rate of 74.1%and an accuracy rate of 94.0%on the traffic signage dataset,which were 3.7,2.8,and 3.4 percentage points higher than the original algorithm,re-spectively.关键词
交通标识检测/小目标检测/YOLOv5s/注意力机制/特征提取/混合空洞空间金字塔池化Key words
traffic sign detection/small target detection/YOLOv5s/attention mechanism/feature extraction/hybrid atrous spatial pyramid pooling(HASPP)分类
信息技术与安全科学引用本文复制引用
李孟浩,袁三男..基于改进YOLOv5s的交通标识检测算法[J].南京信息工程大学学报,2024,16(1):11-19,9.
