一种单阶段无监督可见光-红外跨模态行人重识别方法  

Single Stage Unsupervised Visible-infrared Person Re-identification

作　　者：娄刃 和任强 赵三元[2,3] 郝昕 周跃琪 汪心渊 李方芳 LOU Ren;HE Renqiang;ZHAO Sanyuan;HAO Xin;ZHOU Yueqi;WANG Xinyuan;LI Fangfang(Zhejiang Academy of Transportation Sciences,Hangzhou 310000,China;School of Computer Science,Beijing Institute of Technology,Beijing 100081,China;Yangtze River Delta Research Institute(Jiaxing),Beijing Institute of Technology,Jiaxing,Zhejiang 314011,China;Enterprise Institute of Zhejiang Communications Investment Expressway Operation Management Co.Ltd,Hangzhou 310000,China)

机构地区：[1]浙江省交通运输科学研究院,杭州310000 [2]北京理工大学计算机学院,北京100081 [3]北京理工大学长三角研究院(嘉兴),浙江嘉兴314011 [4]浙江交投高速公路运营管理有限公司企业研究院,杭州310000

出　　处：《计算机科学》2024年第S01期528-534,共7页Computer Science

基　　金：浙江省交通运输厅科技计划项目:交通流雷视融合感知系统评测技术研究(202209);浙江省科学技术厅公益性项目:基于雷视一体设备的车辆轨迹数据质量评测技术研究(LGC22E080003)。

摘　　要：无监督“可见光-红外”跨模态行人重识别任务能够缓解智能监控场景中需要大量人工标注的问题。常见多阶段模型用于处理不同模态数据。文中提出了一种有效的单阶段无监督跨模态行人重识别的方法,设计了基于置信因子的聚类算法和图嵌入的跨模态特征处理方法,分别用于解决无标签问题和跨模态问题。实验结果表明,相较于现有算法,所提方法在r=1时精度至少取得了7%的提高。The unsupervised visible-infrared multi-modal person re-identification can alleviate the problem that a lot of manual labeling is required in the intelligent monitoring scene.Common multi-stage models are used to process different modal data separately.This paper proposes an effective single-stage unsupervised cross-modal pedestrian recognition method,and designs a clustering algorithm based on confidence factor and a cross-modal feature processing method based on graph embedding to solve the unlabeled problem and cross-modal problem respectively.Experimental results show that compared with the existing algorithms,the proposed algorithm has achieved an improvement of at least 7%in the case of r=1.

关 键 词：跨模态学习 无监督行人重识别 可见光-红外行人重识别 无监督学习 跨模态特征处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]