点击次数：

论文类型：期刊论文

发表时间：2017-01-01

发表刊物：IEEE TRANSACTIONS ON IMAGE PROCESSING

收录刊物：SCIE、EI、Scopus

卷号：26

期号：1

页面范围：23-34

ISSN号：1057-7149

关键字：Person re-identification; latent variables; metric learning; spatial misalignments

摘要：In this paper, we propose an effective person re-identification method with latent variables, which represents a pedestrian as the mixture of a holistic model and a number of flexible models. Three types of latent variables are introduced to model uncertain factors in the re-identification problem, including vertical misalignments, horizontal misalignments and leg posture variations. The distance between two pedestrians can be determined by minimizing a given distance function with respect to latent variables, and then be used to conduct the re-identification task. In addition, we develop a latent metric learning method for learning the effective metric matrix, which can be solved via an iterative manner: once latent information is specified, the metric matrix can be obtained based on some typical metric learning methods; with the computed metric matrix, the latent variables can be determined by searching the state space exhaustively. Finally, extensive experiments are conducted on seven databases to evaluate the proposed method. The experimental results demonstrate that our method achieves better performance than other competing algorithms.