This paper has two goals. The rst is to develop a variety of robust methods for the computation of the Fundamental Matrix, the calibration-free representation of camera motion. The methods are drawn from the principal categories of robust estimators, viz case deletion diagnostics, M-estimators and random sampling, and the paper develops the theory required to apply them to non-linear orthogonal regression problems. Although a considerable amount of interest has focussed on the application of robust estimation in computer vision, the relative merits of the many individual methods are unknown, leaving the potential practitioner to guess at their value. The second goal is therefore to compare and judge the methods. Comparative tests are carried out using correspondences generated both synthetically in a statistically controlled fashion and from feature matching in real imagery. In contrast with previously reported methods the goodness of t to the synthetic observations is judged not in terms of the t to the observations per se but in terms of t to the ground truth. A variety of error measures are examined. The experiments allow a statistically satisfying and quasi-optimal method to be synthesized, which is shown to be stable with up to 50 percent outlier contamination, and may still be used if there are more than 50 percent outliers. Performance bounds are established for the method, and a variety of robust methods to estimate the standard deviation of the error and covariance matrix of the parameters are examined. The results of the comparison have broad applicability to vision algorithms where the input data are corrupted not only by noise but also by gross outliers. 1.
|
4345
|
Maximum likelihood from incomplete data via the EM algorithm
– Dempster, Laird, et al.
- 1977
|
|
1143
|
Matrix Computations
– Golub, Loan
- 1989
|
|
1020
|
Numerical Recipes in C: The Art of Scientific Computing
– Press, Teukolsky, et al.
- 1993
|
|
953
|
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
– Fischler, Bolles
- 1981
|
|
905
|
Robust Statistics
– Huber
- 1981
|
|
684
|
Robust regression and outlier detection
– ROUSSEEUW, LEROY
- 1987
|
|
677
|
Computer Vision
– Ballard, Brown
- 1982
|
|
483
|
A computer algorithm for reconstruction of a scene from two projections
– Longuet-Higgins
- 1981
|
|
476
|
What can be seen in three dimensions with an uncalibrated stereo rig
– Faugeras
- 1992
|
|
459
|
Tracking and Data Association
– Bar-Shalom, Fortmann
- 1988
|
|
320
|
Robust Statistics: The Approach Based on Influence Functions
– Hampel, Rousseeuw, et al.
- 1986
|
|
249
|
Estimating threedimensional motion parameters of a rigid planar patch, II: Singular value decomposition
– Tsai, Huang, et al.
- 1982
|
|
236
|
Estimation of relative camera positions for uncalibrated cameras
– Hartley
- 1992
|
|
209
|
Robust Regression Methods for Computer Vision
– Meer, Mintz, et al.
- 1991
|
|
181
|
3D model acquisition from extended image sequences
– Beardsley, Torr, et al.
- 1996
|
|
181
|
Statistical Optimization for Geometric Computation: Theory and Practice
– Kanatani
- 1996
|
|
170
|
Estimation of Planar Curves, Surfaces, and Nonplanar Space Curves Defined by Implicit Equations with Applications to Edge and Range Image Segmentation
– Taubin
- 1991
|
|
145
|
Motion and structure from two perspective views: Algorithms, error analysis, and error estimation
– Weng, Huang, et al.
- 1989
|
|
135
|
Geometric Computation for Machine Vision
– Kanatani
- 1995
|
|
122
|
Optimal motion and structure estimation
– Weng, Ahuja, et al.
- 1993
|
|
106
|
Numerical Recipes in C: The Art of Scienti c Computing
– Press, Flannery, et al.
- 1992
|
|
101
|
Fitting Conic Sections to Scattered Data
– Bookstein
- 1979
|
|
94
|
On lines and planes of closest fit to systems of points in
– Pearson
- 1901
|
|
85
|
On determining the fundamental matrix: Analysis of different methods and experimental results
– Luong, Deriche, et al.
- 1993
|
|
81
|
Outlier detection and motion segmentation
– Torr, Murray
- 1993
|
|
81
|
Direct Least-Squares Fitting of Algebraic Surfaces
– Pratt
- 1987
|
|
77
|
Fitting conic sections to very scattered data: an iterative refinement of the Bookstein algorithm
– Sampson
- 1982
|
|
76
|
Data Analysis and Regression
– Mosteller, Tukey
- 1977
|
|
64
|
Robust methods for estimating pose and a sensitivity analysis
– Kumar, Hanson
- 1994
|
|
50
|
Matrice Fondamentale et Calibration Visuelle sur l’environnement: Vers use plus grande autonomie des systemes robotiques
– Luong
- 1992
|
|
48
|
MINPRAN, a new robust estimator for computer vision
– Stewart
- 1995
|
|
39
|
Elements of Statistical Computing
– Thisted
- 1988
|
|
37
|
Extracting geometric primitives
– Roth, Levine
- 1993
|
|
37
|
Multi-frame approach to visual motion perception
– Spetsakis, Aloimonos
- 1991
|
|
34
|
Statistical bias of conic fitting and renormalization
– Kanatani
- 1994
|
|
29
|
Triangulation
– Hartley, Sturm
- 1994
|
|
27
|
Fast Hough transforms: A hierarchical approach
– Li, Lavin, et al.
- 1986
|
|
27
|
Robust detection of degenerate configurations for the fundamental matrix
– Torr, Maybank, et al.
- 1996
|
|
26
|
Robust Statistics: The Approach Based on In Functions
– Hampel, Ronchetti, et al.
- 1986
|
|
26
|
Motion clustering using the trilinear constraint over three views
– Torr, Zisserman, et al.
- 1995
|
|
25
|
Robust estimation of dispersion matrices and principal components
– Devlin, Gnanadesikan, et al.
- 1981
|
|
23
|
Rejecting outliers and estimating errors in an orthogonal regression framework
– Shapiro, Brady
- 1995
|
|
21
|
Statistical detection of independent movement from a moving camera
– Torr, Murray
- 1993
|
|
18
|
Algorithms for the solution of the nonlinear least-squares problem
– Gill, Murray
- 1978
|
|
17
|
Epipolar line estimation
– Olsen
- 1992
|
|
16
|
Applied Nonparametric Statistical Methods
– Sprent
- 1989
|
|
14
|
Sensitivity Analysis in Linear Regression
– Chaterjee, Hadi
- 1988
|
|
14
|
Robust detection of degeneracy
– Torr, Zisserman, et al.
- 1995
|
|
11
|
Influence in principal component analysis
– Critchley
- 1985
|
|
7
|
On lines and planes of closest to systems of points in
– Pearson
- 1901
|
