Multi-Shot Human Re-Identification for the Security in Video Surveillance Systems

Keeping a safe city against security breaches and acts of violence is something critical. In a smart video-surveillance system, multi-shot human re-identification is a major challenge because of the large variations in a human's appearance caused by different types of noise such as occlusion, viewpoint and illumination variations. In this paper, we propose a model based-on the analysis of all the video surveillance data extracted from camera networks by exploiting the performance of the space-time covariance descriptor. This model not only deals with one video frame as the majority of models, but also considers all the extracted groups of pictures to implicitly encode the described pedestrian in motion by the integration of time parameter with the appearance features such as color, gradient and LBP, and the clustering step. The experiments conducted on PRID dataset showed the importance of video surveillance data analytics in recognition rates.