A Bayesian Approach to Simultaneous Motion Estimation of Multiple Independently Moving Objects

In this paper, the problem of simultaneous motion estima-tion of multiple independently moving objects is addressed.
A novel Bayesian approach is designed for solving this prob-
lem using the sequential importance sampling (SIS) method.
In the proposed algorithm, a balancing step is added into the
SIS procedure to preserve samples of low weights so that all
objects have enough samples to propagate empirical motion
distributions. By using the proposed algorithm, the relative
motions of all moving objects with respect to camera can be
simultaneously estimated . This algorithm has been tested
on both synthetic and real image sequences. Improved re-
sults have been achieved.