重庆邮电大学学报（自然科学版）2023，Vol.35Issue(6)：1117-1126,10.DOI:10.3979/j.issn.1673-825X.202208020200
基于注意力机制的X光安检图像危险物品检测
Detection of dangerous objects in X-ray security inspection images based on attention mechanism
摘要
Abstract
Aiming at the problems of false detection and missing detection of dangerous objects in X-ray baggage security inspection system,we propose an attention fusion network(AFN),which effectively uses context information and enhances the ability of feature representation.The network integrates multi-squeeze excitation(MSE)module and multi-fusion global attention(MFGA)module on the YOLOv3-SPP architecture.Firstly,the feature extracted by the feature extraction network is fused with the channel information extracted by MSE to obtain the semantic feature with channel globality The MFGA module is set in each detection network branch to effectively integrate the channel and spatial information with deep fea-tures,so that the multi-scale features have three-dimensional globality.Testing on the public SIXray data set shows that the proposed method effectively improves the detection accuracy and recall rate of medium and large targets.The average accu-racy of the model is 51.1％,which is 1.4％higher than the classical YOLOv3-SPP algorithm.It shows that channel atten-tion and spatial attention can effectively enhance the detail information used to detect dangerous goods in the input feature map,and improve the detection performance of the model for medium and large targets.关键词
X光行李安检系统/危险物品检测/通道注意力/空间注意力/通道全局性Key words
X-ray baggage security inspection system/dangerous objects detection/channel attention/spatial attention/channel globality分类
电子信息工程引用本文复制引用
郭豆豆,李国权,黄正文,吴建,庞宇..基于注意力机制的X光安检图像危险物品检测[J].重庆邮电大学学报（自然科学版）,2023,35(6):1117-1126,10.基金项目
国家重点研发计划项目(2019YFC1511300) （2019YFC1511300）
国家自然科学基金项目(61971079)The National Key Research and Development Program(2019YFC1511300) （61971079）
The National Natural Science Founda-tion of China(61971079) （61971079）
