A statistical approach for object motion estimation with MPEG motion vectors

In this paper we propose a statistical approach to estimate the object motion with MPEG motion vectors. A model with two normal distribution terms is applied to represent the simplified object motion. One term models the noises embedded in the motion vector field produced in the encoding stage and the other term models the randomness of the trite object motion. Experiments with vehicle motion estimation from MPEG traffic video are used to evaluate the proposed algorithm. The influence of time window, frame size and reference frame distance are investigated. The vehicle speeds can be estimated with a high accuracy tip to 85% similar to 92%.