Multi-resolution optical flow tracking algorithm based on multi-scale Harris corner points feature
Meng Liu, Chengdong Wu, Yunzhou Zhang · 2008
Multi-resolution optical flow tracking algorithm decomposes the object displacement in the wavelet pyramid, then sparse optical flow based on LK (lucas-kanade) algorithm matches the object feature in all the level of the wavelet pyramid step by step. Steadily tracking rapid motion objects is achieved. As to the feature of motion vehicles, multi-scale Harris corner detection based on wavelet is proposed. Traditional Harris corner detection about omitting corner point and asymmetrical array is improved. It is suitable to extract motion vehicle feature in complicated traffic scene. With the experiment, it can be verified that the corner point is always steady and reliable when the vehicle is turning and moving, and the camera is zooming in and out. The tracking algorithm also can accurately match the feature points with the high real-time performance.