Aligned Local Descriptors and Hierarchical Global Features for Person Re-Identification

Person re-identification aims at identifying the same person from different non-overlapping camera views, in which one of the fundamental issues is to have a robust feature under various conditions. In order to deal with the misaligned problem, most works incline to fuse the feature of less associated patches together. Such strategy might result in the loss of their relative location information and hinder the better performance. Therefore, in this paper we introduce aligned local descriptors to preserve the information of patches’ relative location and design hierarchical global features to improve the robustness of image representation for person re-identification. We attempt to apply affine transformation to our framework and find it effective for resolving the viewpoint and pose changes. Experiments are implemented on three challenging datasets VIPeR, QMUL GRID and CUHK Campus. We obtain competitive or superior performance compared to state-of-the-art methods.