Bayesian algorithms for simultaneous structure from motion estimation of multiple independently moving objects

TitleBayesian algorithms for simultaneous structure from motion estimation of multiple independently moving objects
Publication TypeJournal Articles
Year of Publication2005
AuthorsQian G, Chellappa R, Zheng Q
JournalImage Processing, IEEE Transactions on
Pagination94 - 109
Date Published2005/01//
ISBN Number1057-7149
KeywordsAutomated;Reproducibility of Results;Sensitivity and Specificity;Signal Processing, Bayesian algorithm;clustering algorithm;empirical posterior distribution;feature separation parameter;monocular image sequence;motion estimation;multiple independently moving object;object motion;real-image sequence;sequential importance sampling techniqu, Biological;Models, Computer-Assisted;Imaging, Computer-Assisted;Pattern Recognition, Computer-Assisted;Subtraction Technique;Video Recording;Walking;, Statistical;Movement;Numerical Analysis, Three-Dimensional;Information Storage and Retrieval;Models

The problem of simultaneous structure from motion estimation for multiple independently moving objects from a monocular image sequence is addressed. Two Bayesian algorithms are presented for solving this problem using the sequential importance sampling (SIS) technique. The empirical posterior distribution of object motion and feature separation parameters is approximated by weighted samples. The first algorithm addresses the problem when only two moving objects are present. A singular value decomposition (SVD)-based sample clustering algorithm is shown to be capable of separating samples related to different objects. A pair of SIS procedures is used to track the posterior distribution of the motion parameters. In the second 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 algorithms, the relative motions of all the moving objects with respect to the camera can be simultaneously estimated. Both algorithms have been tested on synthetic and real- image sequences. Improved results have been achieved.