On occlusion-handling for people detection fusion in multi-camera networks

Abstract

In this paper a system for people detection by means of Track-To-Track fusion of multiple cameras is presented. The main contribution of this paper is the evaluation of the fusion algorithm based on real image data. Before the fusion of the tracks an occlusion handling resolves implausible assignments. For the evaluation two test vehicles are equipped with LANCOM® wireless access points, cameras, inertial measurement units (IMU) and IMU enhanced GPS receivers. The people are detected by using an AdaBoost algorithm and the results are tracked with a Kalman filter. The tracked results are transmitted to the opponent vehicle in appropriate coordinates. The final stage of the system consists of the fusion and occlusion handling. © 2011 Springer-Verlag.