Person re-identification with content and context re-ranking

This paper proposes a novel and efficient re-ranking technque to solve the person re-identification problem in the surveillance application. Previous methods treat person re-identification as a special object retrieval problem, and compute the retrieval result purely based on a unidirectional matching between the probe and all gallery images. However, the correct matching may be not included in the top-k ranking result due to appearance changes caused by variations in illumination, pose, viewpoint and occlusion. To obtain more accurate re-identification results, we propose to reversely query every gallery person image in a new gallery composed of the original probe person image and other gallery person images, and revise the initial query result according to bidirectional ranking lists. The behind philosophy of our method is that images of the same person should not only have similar visual content, refer to content similarity, but also possess similar k-nearest neighbors, refer to context similarity. Furthermore, the proposed bidirectional re-ranking method can be divided into offline and online parts, where the majority of computation load is accomplished by the offline part and the online computation complexity is only proportional to the size of the gallery data set, which is especially suited to the real-time required video investigation task. Extensive experiments conducted on a series of standard data sets have validated the effectiveness and efficiency of our proposed method.