Active tracking using Intelligent Fuzzy Controller and kernel-based algorithm
Moteaal Asadi Shirzi, Mohammad Reza Hairi Yazdi · 2011
This paper introduces a practical system by combining an Intelligent Fuzzy Controller and vision processing algorithm to obtain an efficient active tracker. Target tracking performance is heavily dependent on a good blend of vision algorithm and control. Because of performance and computational complexity, many visual tracking algorithms cannot be linked with control systems in the real-time tracking. Robustness and speed are the bottlenecks of current visual tracking algorithms. Here, the target's visual model is used along with a kernel-based searching algorithm and a motion detection module to predict the target position. A model update is also incorporated to recognize when the target's appearance is changing due to variations in its position. An Intelligent Fuzzy Controller (IFC) is also synthesized to reach control performance objectives. The IFC used in this tracking system not only helps to track the target accurately in different situations, but also tries to find the target's presence after track loss. Additionally, the parallel processing technique has also been deployed to provide the desired accuracy and speed in real-time tracking. The idea has been implemented in an active camera system to track moving targets.