Abstract

this paper we place the three problems into a common statistical framework; investigating the use of information criteria and robust mixture models as a principled way for motion segmentation of images. The final result is a general fully automatic algorithm for clustering that works in the presence of noise and outliers. 1. Introduction

Citations

6232	Maximum likelihood from incomplete data via the EM algorithm - Dempster, Laird, et al. - 1977
1752	Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography - Fischler, Bolles - 1981
1581	Estimating the dimension of a model - SCHWARZ - 1978
1391	Robust Statistics - Huber - 1981
1131	A new look at the statistical model identification - Akaike - 1974
892	Modeling by shortest data description - Rissanen - 1978
460	What can be seen in three dimensions with an uncalibrated stereo rig - Faugeras - 1992
449	Robust Statistics: the Approach Based on Influence Functions, Wiley Series in probability and mathematical statistics - Hampel, Rousseeuw, et al. - 1986
430	The robust estimation of multiple motions: parametric and piecewise-smooth flow fields. Computer Vision and Image Understanding - Black, Anandan
376	Mixture Models: Inference and Applications to Clustering - McLachlan, Basford - 1988
316	A formal theory of inductive inference - Solomonoff - 1964
253	I.: Estimation of relative camera position for uncalibrated cameras - HARTLEY - 1992
208	Statistical Optimization for Geometric Computation: Theory and Practice - Kanatani - 1996
208	Geometric Invariance in Computer Vision - Mundy, Zisserman - 1992
195	Constructing simple stable descriptions for image partitioning - Leclerc - 1989
176	Layered representation of motion video using robust maximum-likelihood estimation of mixture models and mdl encoding - Ayer, Sawhney - 1995
133	Mixture Models for Optical Flow Computation - Jepson, Black - 1993
130	Some comments on Cp - Mallows - 1973
124	Model selection and Akaike’s Information Criterion (AIC): the general theory and its analytical extensions. Psychometrika 52:345–370 - Bozdogan - 1987
93	Outlier Detection and Motion Segmentation - Torr - 1995
51	S.: An assessment of information criteria for motion model selection - TORR - 1997
47	Thresholding for change detection, in - Rosin - 1998
44	Robust computation and parametrization of multiple view relations - Torr, Zisserman - 1998
40	Segmentation by minimal description - Darrell, Sclaroff, et al. - 1990
29	3d model aquisition from extended image sequences - Beardsley, Torr, et al. - 1996
29	Robust Detection of Degenerate Configurations for the Fundamental - Torr, Zisserman, et al. - 1998
20	Segmentation as the search for the best description of the image in terms of primitives - Leonardis, Gupta, et al. - 1990
16	A review of robust methods to estimate the fundamental matrix. Accepted to IJCV - Torr, Murray - 1996
5	An information theoretic robust sequential procedure for surface model order selection in noisy range data - Mirza, Boyer - 1992
2	MDL-based segementation and motion modeling in a long image sequence of scene with multiple independently moving objects - Gu, Yoshiaki, et al. - 1996