Minimizing Maximum Feature Space Deviation for Visible-Infrared Person Re-Identification

Abstract

Visible-infrared person re-identification (VIPR) has great potential for intelligent video surveillance systems at night, but it is challenging due to the huge modal gap between visible and infrared modalities. For that, this paper proposes a minimizing maximum feature space deviation (MMFSD) method for VIPR. First, this paper calculates visible and infrared feature centers of each identity. Second, this paper defines feature space deviations based on these feature centers to measure the modal gap between visible and infrared modalities. Third, this paper minimizes the maximum feature space deviation to significantly reduce the modal gap between visible and infrared modalities. Experimental results show the superiority of the proposed method, e.g., on the RegDB dataset, the rank-1 accuracy reaches 92.19%.