Projection with Gaussian Kernel for Person Re-Identification

Abstract

Person re-identification (ReID), the task of associating the detected images of a person as he/she moves in a non-overlapping camera network, is faced with different challenges including variations in the illumination, view-point and occlusion. To ensure good performance for person ReID, the state-of-the-art methods have leveraged different characteristics for person representation. As a result, a high-dimensional feature vector is extracted and used in the person matching step. However, each feature plays a specific role for distinguishing one person from the others. This paper proposes a method for person ReID wherein the correspondences between descriptors in high-dimensional space can be achieved via explicit feature selection and appropriate projection with a Gaussian kernel. The advantage of the proposed method is that it allows simultaneous matching of the descriptors while preserving the local geometry of the manifolds. Different experiments were conducted on both single-shot and multi-shot person ReID datasets. The experimental results demonstrates that the proposed method outperforms the state-of-the-art methods.