基于双流结构的跨模态行人重识别关系网络  

Cross-modal person re-identification relation network based on dual-stream structure

作　　者：郭玉彬[1,2] 文向 刘攀 李西明[1,2] GUO Yubin;WEN Xiang;LIU Pan;LI Ximing(College of Mathematics and Informatics,South China Agricultural University,Guangzhou Guangdong 510642,China;Guangzhou Key Laboratory of Intelligent Agriculture(South China Agricultural University),Guangzhou Guangdong 510642,China)

机构地区：[1]华南农业大学数学与信息学院,广州510642 [2]广州市智慧农业重点实验室(华南农业大学),广州510642

出　　处：《计算机应用》2023年第6期1803-1810,共8页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61872152);广州市科技计划项目(201902010081)。

摘　　要：针对可见光-红外跨模态行人重识别中模态差异导致的识别精确率低的问题,提出了一种基于双流结构的跨模态行人重识别关系网络(IVRNBDS)。首先,利用双流结构分别提取可见光模态和红外模态行人图像的特征;然后,将行人图像的特征图水平切分为6个片段,以提取行人的每个片段的局部特征和其他片段的特征之间的关系,以及行人的核心特征和平均特征之间的关系;最后,在设计损失函数时,引入异质中心三元组损失(HC Loss)函数放松普通三元组损失函数的严格约束,从而使不同模态的图像特征可以更好地映射到同一特征空间中。在公开数据集SYSU-MM01(Sun Yat-Sen University Multi Modal re-identification)和Reg DB(Dongguk Body-based person Recognition)上的实验结果表明,虽然IVRNBDS的计算量略高于当前主流的跨模态行人重识别算法,但所提网络在相似度排名第1(Rank-1)指标和平均精度均值(m AP)指标上都有所提高,提高了跨模态行人重识别算法的识别精确率。In visible-infrared cross-modal person re-identification,the modal differences will lead to low identification accuracy.Therefore,a dual-stream structure based cross-modal person re-identification relation network,named IVRNBDS(Infrared and Visible Relation Network Based on Dual-stream Structure),was proposed.Firstly,the dual-stream structure was used to extract the features of the visible light modal and the infrared modal person images respectively.Then,the feature map of the person image was divided into six segments horizontally to extract relationships between the local features of each segment and the features of other segments of the person and the relationship between the core features and average features of the person.Finally,when designing loss function,the Hetero-Center triplet Loss(HC Loss)function was introduced to relax the strict constraints of the ordinary triplet loss function,so that image features of different modals were able to be better mapped into the same feature space.Experimental results on public datasets SYSU-MM01(SunYat-Sen University MultiModal re-identification)and RegDB(Dongguk Body-based person Recognition)show that the computational cost of IVRNBDS is slightly higher than those of the mainstream cross-modal person re-identification algorithms,but the proposed network has the Rank-1(similarity Rank 1)and mAP(mean Average Precision)improved compared to the mainstream algorithms,increasing the recognition accuracy of the cross-modal people re-identification algorithm.

关 键 词：行人重识别 可见光-红外跨模态 双流结构 异质中心三元组损失 局部特征 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]