People Re-Identification in Video Surveillance Systems Using Angle Information

Intelligent video surveillance is one of the main applications in machine vision. People re-identification as part of these systems is of particular importance. Indeed, the accuracy in this part improves the efficiency of many types of monitoring algorithms. The re-identification task in human mind is performed consciously and is based on a prior knowledge of the 3D attributes of the human body. One of these attributes is the orientation of the body relative to the camera. In other words, a human supervisor at the matching stage uses the angle information to estimate the appearance of the person at different angles. In this research, the above process is modeled. Thus, in this research, a fully informed approach is provided to eliminate the destructive effects of angular changes of the person in the re-identification process. For this purpose, upper part of person's body clothing that can be seen or hidden from different angles are extracted and used in the matching stage. For evaluation and comparison, the proposed method was used in two of the most efficient re-identification algorithms. Experiments were performed on the ViPer dataset and the results show improvements in the recognition rate.