Global motion estimation from coarsely sampled motion vector field and the applications

Global, motion estimation is a powerful tool widely used in video Processing and compression as well as in computer vision areas. In this paper, we propose a new approach for estimating global motions from coarsely sampled motion vector fields. The proposed method minimizes the fitting error between the input motion vectors and the motion vectors generated from the estimated motion model using the Newton-Raphson method with outlier rejections. Applications of the proposed method in video coding include fast global motion estimation for MPEG-4 Advanced Simple Profile coding, MPEG-2 to MPEG-4 ASP transcoding, and error concealments. Simulation results and analyses are provided for the proposed method and the applications, which show the effectiveness of the method in terms of accuracy, robustness, and speed.