A statistical approach for object motion estimation with MPEG motion vectors

We propose a statistical approach to estimate 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 noise embedded in the motion vector field produced at the encoding stage and the other term models the randomness of the true 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 of up to 85-92%