Estimation of motion using motion blur for tracking vision system

In this paper, we propose a novel algorithm for the optical flow estimation of a moving object by using the motion blur in a scene. The proposed technique is applied to the visual tracking system for the object moving on the 2D plane that is perpendicular to the axis of lens of a camera. To estimate the motion parameters, we use the motion blur, which has been treated as noises under the conventional method. And we use the feature of motion blur in the frequency domain. The first step is the estimation of orientation of motion, which is achieved by computing the log power spectrum of a local image patch, and operating the coordinate transformation. The second step is the estimation of velocity by using the cepstral analysis. It is achieved by detecting the period of sine function relating to the length of motion blur. In order to evaluate the feasibility of the proposed algorithm, we investigate the accuracy of the estimated optical flow with artificial blurred images and real images. And we apply the proposed algorithm to the tracking vision system, which consists of a camera performing the pan motion, a video processing board, and a standard PC. Through some experiments, we show that the proposed technique is advantageous to the high-speed-tracking system.