融合高效通道注意力的复杂场景违禁品检测
Detection of prohibited items in complex scenes with integrated efficient channel attention
崔丽群 1李万欣1
作者信息
- 1. 辽宁工程技术大学 软件学院,辽宁 葫芦岛 125105
- 折叠
摘要
针对X射线在违禁品检测任务中安检图像色彩存在对比度低、检测精度低、极易出现漏检错检的问题,在快速区域卷积神经网络(Faster R-CNN)算法基础上,通过K-means聚类算法改进锚框(Anchor)的生成方式;提出将高效通道注意力机制(ECANet)引入到感兴趣池化层(ROIpooling)后,突出违禁品的轮廓、色彩等信息.本文算法在S_DXray数据集上的mAP达到 92.06%,改进后网络模型检测精度提高 5.06 个百分点.有效提高X射线图像违禁品检测的精度和小尺度目标的检测能力,有效避免错检、漏检的现象.
Abstract
Aiming at the problems of low contrast,low detection accuracy and easy to miss detection and error detection of X-ray security image color in contraband detection task,based on Faster R-CNN algorithm,K-means clustering algorithm is used to improve the generation method of Anchor.It is proposed to introduce the efficient channel attention mechanism(ECANet)into the ROI pooling layer to highlight the contour,color and other information of contraband.The mAP of the proposed algorithm on the S_DXray dataset reaches 92.06%,and the detection accuracy of the improved network model is improved by 5.06 percentage points.It effectively improves the accuracy of X-ray image contraband detection and the detection ability of small-scale targets,and effectively avoids the phenomenon of false detection and missed detection.
关键词
目标检测/X射线图像/残差网络/特征金字塔/K均值聚类/快速区域卷积神经网络/高效通道注意力机制Key words
target detection/X-ray images/ResNet/FPN/K-means/Faster R-CNN/ECANet引用本文复制引用
基金项目
辽宁省高等学校基本研究项目(LJKMZ20220699)
出版年
2024
国家科技期刊平台
NSTL
万方数据