An improved moving target detecting and tracking based on Optical Flow technique and Kalman filter

Optical flow is a well known method for motion estimation and explanation. We can use it to detect and track the moving target, as it always reflects to the motion field of the captured scene in the image. In this paper, we first propose an improved optical flow method which is based on the technology of point matching and the strategy of uniform sampling. Then the goal of detecting and tracking moving target is achieved efficiently by the proposed method in the graying flow field. Especially, the detecting and tracking are improved due to the introduction of Kalman filter. Experiments show that, the calculation speed of our proposed method is relatively high and our approach can successfully detect and track moving targets in a real time.