Learning Visual-Spatial Saliency for Multiple-Shot Person Re-Identification

Recognizing persons across non-overlapping camera views, known as person re-identification, has received increasing attentions for its importance in many surveillance applications. However, most of existing methods rely on pre-training steps to ensure their performance and ignore the body prior knowledge of pedestrians. In this letter, we propose a novel non-training method for person re-identification which learns visual-spatial saliency from voter images and the given query image. First we segment pedestrian images into small regions and use two hypergraphs to represent the visual and spatial relationship among regions. Then we formulate the visual-spatial saliency learning as a joint hypergraph ranking problem by simultaneously considering the human body prior and the appearance similarity among pedestrians. Finally, the visual-spatial saliency is incorporated in region-based matching to improve the performance of person re-identification. Experimental evaluation on three publicly available datasets demonstrates the effectiveness of our approach.