<title>Outlier detection and motion segmentation</title>

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEPublished 20 August 1993

Philip H. S. Torr, David W. Murray

DOI10.1117/12.150246

Source URL

Citations209

SJR score0.15

SNIP0.20

TL;DR

A new method for solving the problem of motion segmentation, identifying the objects within an image moving independently of the background by utilizing the fact that two views of a static 3D point set are linked by a 3 X 3 Fundamental Matrix (F).

Abstract

We present a new method for solving the problem of motion segmentation, identifying the objects within an image moving independently of the background. We utilize the fact that two views of a static 3D point set are linked by a 3 X 3 Fundamental Matrix (F). The Fundamental Matrix contains all the information on structure and motion from a given set of point correspondences and is derived by a least squares method under the assumption that the majority of the image is undergoing a rigid motion. Least squares is the most commonly used method of parameter estimation in computer vision algorithms. However the estimated parameters from a least squares fit can be corrupted beyond recognition in the presence of gross errors or outliers which plague any data from real imagery. Features with a motion independent of the background are those statistically inconsistent from the calculated value of (F). Well founded methods for detecting these outlying points are described.

Keywords

Computer Science

Communications of the ACMRandom sample consensus

25,463 Citations1981Martin A. Fischler, Robert C. Bolles

New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.

View PDF

TechnometricsRobust Regression and Outlier Detection

6,183 Citations1989Gregory F. Piepel, Peter J. Rousseeuw +1 more

Lecture notes in computer scienceWhat can be seen in three dimensions with an uncalibrated stereo rig?

833 Citations1992Olivier Faugeras

This paper addresses the problem of determining the kind of three- dimensional reconstructions that can be obtained from a binocular stereo rig for which no three-dimensional metric calibration data is available, and shows that even in this case some very rich non-metric reconstructions of the environment can nonetheless be obtained.

Computer Graphics and Image ProcessingFitting conic sections to “very scattered” data: An iterative refinement of the bookstein algorithm

349 Citations1982Paul D. Sampson

An examination of the geometric interpretation of the error-of-fit measure of the Bookstein algorithm for fitting conic sections shows why it may not be entirely satisfoctory when the data are “very scattere” in the sense that the data points are distributed rather widely about an underlying smooth curve.

Elements of Statistical Computing

338 Citations2017Ronald A. Thisted

IEEE Transactions on Pattern Analysis and Machine IntelligenceInherent ambiguities in recovering 3-D motion and structure from a noisy flow field

271 Citations1989Gilad Adiv

Two problems which may arise due to the presence of noise in the flow field are examined and constraints and parameters which can be recovered even in ambiguous situations are presented.

IEEE Transactions on Pattern Analysis and Machine IntelligenceBinocular Image Flows: Steps Toward Stereo-Motion Fusion

184 Citations1986Allen M. Waxman, James H. Duncan

A new module is described here which unifies stereo and motion analysis in a manner in which each helps to overcome the other's short-comings and points to the importance of the ratio, rate of change of disparity, and its possible role in establishing stereo correspondence.

IEEE Transactions on Pattern Analysis and Machine IntelligenceDynamic Occlusion Analysis in Optical Flow Fields

156 Citations1985William B. Thompson, Kathleen M. Mutch +1 more

An edge detection algorithm sensitive to changes in flow fields likely to be associated with occlusion, patterned after the Marr-Hildreth zero-crossing detectors currently used to locate boundaries in scalar fields is derived.

Affine and Projective Structure from Motion

45 Citations1992Sabine Demey, Andrew Zisserman +1 more

Pattern Recognition LettersDetecting the image boundaries between optical flow fields from several moving planar facets

13 Citations1986David W. Murray, N S Williams

A novel method of image and scene segmentation is presented which detects boundaries in the image between optical flow fields from different moving planar facets in the scene.

&lt;title&gt;Outlier detection and motion segmentation&lt;/title&gt;

TL;DR

Abstract

Keywords

<title>Outlier detection and motion segmentation</title>