基于改进Cascade RCNN网络的X光安检违禁品检测  

X-ray Security Inspection for Contraband Detection Based on Improved Cascade RCNN Network

作　　者：张娜[1] 罗源 包晓安[1] 金瑜婷 涂小妹 ZHANG Na;LUO Yuan;BAO Xiao-An;JIN Yu-Ting;TU Xiao-Mei(School of Information Science and Technology,Zhejiang Sci-Tech University,Hangzhou 310018,China;Zhejiang Guangsha Vocational and Technical University of Construction,Dongyang 322100,China)

机构地区：[1]浙江理工大学信息学院,杭州310018 [2]浙江广厦建设职业技术大学,东阳322100

出　　处：《计算机系统应用》2022年第7期224-230,共7页Computer Systems & Applications

基　　金：浙江省重点研发计划(2020C03094);国家自然科学基金(6207050141)。

摘　　要：针对X光安检违禁品检出率低下的问题,提出了一种基于改进Cascade RCNN网络的X光安检违禁品检测算法.该算法在网络结构上引入批特征擦除(batch feature erasing,BFE)模块.BFE模块通过随机擦除相同区域来增强局部特征学习,进而强化网络对剩余特征的学习表达.此外,针对检出率低下问题,在该算法中提出加权SD loss损失函数,该损失函数使用权重融合的方式将Smooth L1 loss与DIoU loss进行加权融合,通过改变权重比例系数,能够使目标检测结果更加准确,一定程度上提高了检出率.实验结果表明:在公开的X光安检违禁品数据集上,测试性能与原算法相比,改进Cascade RCNN网络对X光安检违禁品检出率增长了3.11%,改进算法的识别精度有一定的提高.Considering the low detection rate of X-ray security inspection of contraband,an algorithm based on the improved Cascade RCNN is proposed.By this algorithm,a batch feature erasing(BFE)module is introduced into the network structure,which can enhance local feature learning by randomly erasing the same region and thus further enhance the learning expression of residual features.In addition,the weighted SD loss function is presented in this algorithm to solve the problem of low detection rates,which employs weight fusion to fuse Smooth L1 loss and DIoU loss,and by changing the proportion coefficient of weights,it can make the detection result more accurate.The experimental results show that the detection rate of the improved Cascade RCNN on an open contraband dataset for X-ray security inspection is increased by 3.11%compared with that of the original algorithm,and the accuracy of the improved algorithm is raised.

关 键 词：X光安检图像 批特征擦除 SD loss损失函数 安检违禁品检测 Cascade RCNN 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] O434.19[自动化与计算机技术—计算机科学与技术]