Learning Cross-View Binary Identities for Fast Person Re-Identification

In this paper, we propose to learn cross-view binary identities (CBI) for fast person re-identification. To achieve this, two sets of discriminative hash functions for two different views are learned by simultaneously minimising their distance in the Hamming space, and maximising the cross-covariance and margin. Thus, similar binary codes can be found for images of a same person captured at different views by embedding the images into the Hamming space. Therefore, person re-identification can be solved by efficiently computing and ranking the Hamming distances between the images. Extensive experiments are conducted on two public datasets and CBI produces comparable results as state-ofthe- art re-identification approaches but is at least 2200 times faster.