A spatio-temporal covariance descriptor for person re-identification

In intelligent video surveillance systems, tracking people in non overlapping camera networks is a major challenge. To deal with the change of illumination, occlusion, change of view, etc., it is essential to seek the most robust object descriptor invariant during changes. By exploiting the performance of covariance descriptor, we propose a spatio-temporal covariance descriptor. This descriptor deals not only one picture as the majority of descriptors, but also considers groups of pictures to implicitly encode the described object motion by the integration of time parameter. The experiments conducted on << CAVIAR4REID >> database showed these improvements. The person recognition rate in the first rank is improved by more than 10% compared to other descriptors.