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

In thispaper, the problem ofsimultaneousmotionestimation of multiple independently moving objects is addressed. A novel Bayesian approach is designedfor solvingthisproblem using the sequentialimportance sampling (SIS) method. In the proposed algorithm,a balancingstep is added intothe 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 results have been achieved.

• Type: Conference
• Year: 2002
• Where: ICPR
• Authors: Gang Qian, Rama Chellappa, Qinfen Zheng
• Keywords: Computer Vision, Empirical Motion Distributions, ICPR 2002, Intothe Sis Procedure, Real Image Sequences