基于可见光-红外模态下双向特征生成的行人重识别方法  

Person re-identification method based on Visible-Infrared modal bidirectional feature generation

作　　者：王晓红[1] 李超奇 卢辉 WANG Xiaohong;LI Chaoqi;LU Hui(College of Communication and Art Design,University of Shanghai for Science and Technology,ShangHai 200125,China;Wuhan Optics Valley Aerospace SanJiang laser Industrial Technology Research Institute,WuHan 430075,China)

机构地区：[1]上海理工大学出版印刷与艺术设计学院,上海200125 [2]武汉光谷航天三江激光产业技术研究院有限公司,武汉430075

出　　处：《光学技术》2022年第3期372-378,共7页Optical Technique

基　　金：国家新闻出版署智能与绿色柔版印刷重点实验室招标课题资助项目(ZBKT202108)。

摘　　要：为了提高可见光-红外跨模态行人重识别的检测准确度,提出一种基于可见光-红外模态双向特征生成的双流网络模型,相对现有算法,使用双向特征生成方法进行跨模态行人特征迁移,显著提高了跨模态特征表达,同时利用双流网络提取具有判别性双模态特征,并通过设计的粗细粒度损失融合的策略,提高了跨模态行人检索的准确度。实验结果表明,与最新方法相比,文章提出的方法提高了跨模态行人重识别的平均准确度,在RegDB数据集上取得92.91%,在SYSU-MM01数据集取得66.17%。In order to improve the detection accuracy of Visible-Infrared Cross-modal Person re-identification,a dual flow network model based on Visible-Infrared Cross-modal bidirectional feature generation is proposed.Compared with the existing algorithms,employ the bidirectional feature generation method to transfer the Cross-modal pedestrian features,which significantly enhances the Cross-modal feature expression.At the same time,the dual flow network is used to extract the discriminative dual-modal features,and the coarse-grained and fine-grained loss fusion strategy designed improves the accuracy of cross-modal pedestrian retrieval.The experimental results indicate that compared with the latest method,the average accuracy of cross modal pedestrian recognition,92.91%on RegDB and 66.17%on SYSU-MM01,is increased effectively by proposed method.

关 键 词：行人重识别 特征迁移 深度学习 生成对抗网络 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]