Object tracking from stereo sequences using particle filter

In this paper we present a vehicle tracking particle filter system based on gray histogram and sparse optical flow detection in stereo images. The proposed approach is based on the fact that for 2D tracked features we can compute their 3D correspondences, which are used for particle filter tracking improvement. The goal of this paper is to show how vision based particle filter tracking, optical flow and stereovision can be integrated to work together in order to achieve a robust object tracking algorithm.