A Factorization Method for Multibody Motion Estimation and Segmentation

Rene Vidal and Stefano Soatto1
(Professor S. Shankar Sastry)
(ONR) N00014-00-1-0621

We study the problem of estimating the motion of independently moving objects observed by a moving perspective camera. We show that infinitesimal image measurements corresponding to independent motions lie on orthogonal six-dimensional subspaces of a higher-dimensional linear space. We propose a factorization algorithm that estimates the number of independent motions, the segmentation of the image points, and the motion of each object relative to the camera from a set of image points and their optical flows in multiple frames. We evaluate the proposed algorithm on synthetic and real image sequences.


Figure 1: Segmentation of two independent motions: the camera and the car.

[1]
R. Vidal, S. Soatto, and S. Sastry, "A Factorization Method for Multibody Motion Estimation and Segmentation," Allerton Conf., Monticello, IL, October 2002.
1Professor, University of California at Los Angeles

More information (http://www.eecs.berkeley.edu/~rvidal/) or

Send mail to the author : (rvidal@eecs.berkeley.edu)


Edit this abstract