This paper investigates real-time target determination, recognition and tracking with an airborne video system. The visual navigation and target tracking in an unmanned aerial vehicle (UAV) are of great interest among scientists. To achieve real-time target determination and tracking, we have to accomplish two missions: to determine the “feature” of the target in real time, and to update the the “feature”. This paper develops an algorithm to define the feature of the target in real time. With experiment data, we also demonstrate the validity of our algorithms. Our algorithm is potentially applicable to airborne video tracking system in a UAV.
11th IEEE International Conference on Control & Automation, pp.1363-1368