Fuzzy control for obstacle detection in object tracking

One of the typical objectives of the computer vision is the object tracking in a video sequence [1]. This technology has many applications in diverse fields. We have studied a fast and robust object tracking system based on optical flow. To solve the occlusion problem, we have developed a combined tracking sys-tem based on optical flow and adaptive filters or neural networks [2]. The critical point of the system is the coupling between optical flow and predictive algorithms. This coupling is governed by parameters such as tolerance, the absolute value of the difference between the value of velocity calculated by the optical flow and the estimated value. We propose the use of a fuzzy control system [3] to solve this coupling problem between the different velocities. This technique will provide great robustnes