Fuzzy control for obstacle detection in stereo video sequences

One of the most important problems in 3D tracking is the occlusion effect produced by obstacles. To solve this problem, we have developed a tracking system based on optical flow and stereo vision, combined with adaptive filters to predict the expected 3D velocities of objects. The critical point of the system is the coupling between tracking and predictive algorithms. We propose the use of a fuzzy control system to solve this coupling problem between the different velocities. This technique has been previously tested in 2D video sequences, providing great robustness to the tracking algorithm.