PEOPLE REIDENTIFICATION IN A DISTRIBUTED CAMERA NETWORK

Abstract

This paper presents an approach to the people reidenti fication problem in a distributed camera network system. The reidentifi cation or reacquisition problem consists essentially on the matching process of images acquired from di fferent cameras. This work is applied in a monitored environment by cameras. This application is important to modern security systems, in which the targets presence identi cation in the environment expands the capacity of action by security agents in real time and provides important parameters like localization for each target. We used the target's color and target's interest points with features for reidenti cation. The satisfactory results were obtained from real experiments in public video datasets and synthetic images with noise.