A comparison between person re-identification approaches

Abstract

In this paper, we presented a comparison between different approaches of person re-identification in camera network based on the-state-of-the-art. We studied the different descriptors of objects for identifying people and existing classifier at the re-identification step. We seek to develop video surveillance systems online in controlled areas and improve their reliability and their processing time. We concluded that using the spatio-temporal information of any person and its biometrics behavioral extracted from the video stream and analyzed then through an online classification represent a modern approach.