Person Re-Identification using Reduced Dictionary Sparse Representation Based Classifier

Abstract

Video surveillance has become a necessary tool for monitoring a public places. Automation of the video surveillance is the current need, as it a tough task for the humans to monitor the surveillance video continuously. Also searching a person from a bulk of videos is not an easy job. Person re-identification is a step taken towards to make the video surveillance an automated one. Person re-Identification is a task of matching the identity of a person captured by different cameras in the network at different places and times. The cameras used for surveillance are located at a much higher position than the person so that the conventional method of face recognition is not used for identification of the person. The images of the same person may differ based on the qualities of different cameras (resolution changes), or due to different lighting conditions (variation in illumination) or due to posture changes. Recently sparse based classifier is used in person re-identification and is effective in handling in illumination variation and occlusion. But sparse based decomposition method is not computational efficient. This leads to the development of the person re-identification method based on Reduced Dictionary Sparse representation based Classifier (RDSC). This is done with 2 steps: (i) Similarity score for reduction of the gallery; (ii) Sparse basis expansion of targets in terms of reduced gallery. The proposed method is both computational efficient and creates better outcomes.