Omnidirectional Feature Learning for Person Re-Identification

IEEE Access

卷:7

Yang Zhao¹  Xin-Yong Zhao¹  Jian-Hong Sun¹  Di Wu²  Hong-Wei Yang²  De-Shuang Huang²  Chang-An Yuan³  Xiao Qin³ 

[1] Beijing E-Hualu Information Technology Co., Ltd., Beijing, China;

[2] School of Electronics and Information Engineering, Institute of Machine Learning and Systems Biology, Tongji University, Shanghai, China;

[3] Science Computing and Intelligent Information Processing of Guangxi Higher Education Key Laboratory, Guangxi Teachers Education University, Nanning, China;

关键词: Person re-identification;    deep learning;    part feature;    triplet model;    identification model;   

DOI  :  10.1109/ACCESS.2019.2901764

来源: DOAJ

【 摘 要 】

Person re-identification (PReID) has received increasing attention due to it being an important role in intelligent surveillance. Many state-of-the-art PReID methods are part-based deep models. Most of these models focus on learning the part feature representation of a person's body from the horizontal direction. However, the feature representation of the body from the vertical direction is usually ignored. In addition, the relationships between these part features and different feature channels are not considered. In this paper, we introduce a multi-branch deep model for PReID. Specifically, the model consists of five branches. Among the five branches, two branches learn the part features with spatial information from horizontal and vertical orientations; one branch aims to learn the interdependencies between different feature channels generated by the last convolution layer of the backbone network; the remaining two branches are identification and triplet sub-networks in which the discriminative global feature and a corresponding measurement can be learned simultaneously. All five branches can improve the quality of representation learning. We conduct extensive comparison experiments on three benchmarks, including Market-1501, CUHK03, and DukeMTMC-reID. The proposed deep framework outperforms other competitive state-of-the-art methods. The code is available at https://github.com/caojunying/person-reidentification.

【 授权许可】

Unknown