Learning part-alignment feature for person re-identification with spatial-temporal-based re-ranking method

Zhongyi Li, Yi Jin, Yidong Li, Congyan Lang, Songhe Feng, Tao Wang

Abstract: Person re-identification is to identify a target person in different cameras with non-overlapping views. It is a challenging task due to various viewpoints of persons, diversified illuminations, and complicated environments. In addition, body parts are usually misaligned because of the less precise bounding boxes, which play a significant role in person re-identification, so it is crucial to make them aligned for better performance. In this paper, we propose a network to learn powerful features combining global features and local-alignment features for person re-identification. For each body part, instead of fixed horizontal partition, a key points detection network is adopted to locate body parts that contain more precise and distinctive information. Besides, a novel re-ranking approach is proposed to refine the rough initial rank list by exploiting the spatial-temporal information. Unlike most existing re-ranking based methods fine-tuning the rough initial rank list only by k-nearest neighbors and their k-reverse-nearest neighbors, our method exploits spatial-temporal information which can be easily stored in the name of images, so it can be implemented in any baseline to improve the performance. Experiments on the GRID, Market-1501, and DukeMTMC-reID are conducted to prove the effectiveness of our method.