Vehicle Motion Tracking Using Symmetry of Vehicle and Background Subtraction
Hiroshi Unno, Kouki Ojima, Keikichi Hayashibe, Hitoshi Saji · IEEE Intelligent Vehicles Symposium · 2007
We propose a new method of vehicle motion tracking. In our method, we use the template matching method for tracking. The template matching method has been used in many applications. In vehicle tracking, there are some problems, such as vehicle size change, occlusions, and shaded areas. To solve these problems, we divide and update the template at every frame by the background subtraction method. Moreover, we use the information that the front of the vehicle body is symmetric, and we remove areas other than the vehicle area and update the template correctly. We evaluate the efficacy of our method on several video frames.