PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Incorporating non-motion cues into 3D motion segmentation
Amit Gruber and Yair Weiss
In: ECCV 2006, 7-13 May 2006, Graz, Austria.


We address the problem of segmenting an image sequence into rigidly moving 3D objects. An elegant solution to this problem is the multibody factorization approach in which the measurement matrix is factored into lower rank matrices. Despite progress in factorization algorithms, the performance is still far from satisfactory and in scenes with missing data and noise, most existing algorithms fail. In this paper we propose a method for incorporating 2D non-motion cues (such as spatial coherence) into multibody factorization. We formulate the problem in terms of constrained factor analysis and use the EM algorithm to find the segmentation. We show that adding these cues improves performance in real and synthetic sequences.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:2156
Deposited By:Yair Weiss
Deposited On:18 July 2006