Top distance regularized projection and dictionary learning for person re-identification

Abstract

Person re-identification (PRID) is integral to many smart surveillance systems. However, owing to the visual ambiguities arising from the variability in viewing angles and illumination, and the presence of occlusions, PRID continues to present many challenges, especially when only a single image per view is available for each person. To overcome this problem, we propose a top distance regularized projection and dictionary learning (DL) model for PRID. The model incorporates both projection and DL to form a unified optimization framework to enhance the effectiveness of both these types of learning. Thus, the dictionary and projection matrix are jointly learned within this framework. In particular, the learned projection maps the coding coefficient into a discriminative space and minimizes the distance between the same persons across non-overlapping views such that the dictionary and projection can be discriminated. Moreover, we exploit listwise distances to capture all pairwise similarities. Based on this design, we derive a top distance regularization term to refine the solution space of the DL model such that the discriminative ability of the learned projection matrix and dictionary are further improved. Experiments on different challenging datasets demonstrate the effectiveness of our method and its superiority over a few current state-of-the-art approaches.