Geodesic
Extending RANSAC-based estimators to handle unknown and varying noise level
Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 9 (2006) no. 3, pp. 263-277.

Voir la notice de l'article provenant de la source Math-Net.Ru

The robust parameter estimation methods are a general tool in computer vision, widely used for such tasks as multiple view relation estimation and camera calibration. In this paper, a new robust maximum-likelihood estimator AMLESAC is presented. It is a noise-adaptive version of the well-known MLESAC estimator. It adopts the same sampling strategy and seeks the solution to maximize the likelihood rather than some heuristic measure. Unlike MLESAC, it simultaneously estimates all the noise parameters: inlier share $\gamma$, inlier error standard deviation $\sigma$ and outlier probability density $1/\nu$. Effective optimization for the computation speed-up is also introduced. Results are given both for synthetic and real test data for different types of models. The algorithm is demonstrated to surpass the previous approaches for the task of pose estimation and provides results equal or superior to other robust estimators in other tests. 
@article{SJVM_2006_9_3_a5,
     author = {A. S. Konouchine and V. A. Gaganov and V. P. Vezhnevets},
     title = {Extending {RANSAC-based} estimators to handle unknown and varying noise level},
     journal = {Sibirskij \v{z}urnal vy\v{c}islitelʹnoj matematiki},
     pages = {263--277},
     publisher = {mathdoc},
     volume = {9},
     number = {3},
     year = {2006},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/SJVM_2006_9_3_a5/}
}
TY  - JOUR
AU  - A. S. Konouchine
AU  - V. A. Gaganov
AU  - V. P. Vezhnevets
TI  - Extending RANSAC-based estimators to handle unknown and varying noise level
JO  - Sibirskij žurnal vyčislitelʹnoj matematiki
PY  - 2006
SP  - 263
EP  - 277
VL  - 9
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/SJVM_2006_9_3_a5/
LA  - en
ID  - SJVM_2006_9_3_a5
ER  - 
%0 Journal Article
%A A. S. Konouchine
%A V. A. Gaganov
%A V. P. Vezhnevets
%T Extending RANSAC-based estimators to handle unknown and varying noise level
%J Sibirskij žurnal vyčislitelʹnoj matematiki
%D 2006
%P 263-277
%V 9
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/SJVM_2006_9_3_a5/
%G en
%F SJVM_2006_9_3_a5
A. S. Konouchine; V. A. Gaganov; V. P. Vezhnevets. Extending RANSAC-based estimators to handle unknown and varying noise level. Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 9 (2006) no. 3, pp. 263-277. http://geodesic.mathdoc.fr/item/SJVM_2006_9_3_a5/

[1] Stewart C. V., “Robust parameter estimation in computer vision”, SIAM Review, 41:3 (1999), 513–537 | DOI | MR | Zbl

[2] Illingworth J., Kittler J., “A survey of the Hough transform”, Computer Vision, Graphics, and Image Processing, 44:1 (1988), 87–116 | DOI

[3] Rousseeuw P. J., “Least median of squares regression”, J. of the American Statistical Association, 79 (1984), 871–880 | DOI | MR | Zbl

[4] Fischler M. A., Bolles R. C., “Random Sample Consensus: A paradigm for model fitting with applications to image analysis and automated cartography”, Communications of the ACM, 24:6 (1981), 381–395 | DOI | MR

[5] Torr P., Zisserman A., “Robust computation and parametrization of multiple view relations”, Proc. ICCV'98, 1998, 727–732

[6] Torr P. H. S., Zisserman A., “MLESAC: A new robust estimator with application to estimating image geometry”, Computer Vision and Image Understanding, 78 (2000), 138–156 | DOI

[7] Torr P. H. S., “Bayesian model estimation and selection for epipolar geometry and generic manifold fitting”, Int. J. of Computer Vision, 50:1 (2002), 27–45 | DOI

[8] Feng C. L., Hung Y. S., “Robust method for estimating the fundamental matrix”, Proc. DICTA-2003, 2003, 633–642

[9] Harris C., Stephens M., “A combined corner and edge detector”, Fourth Alvey Vision Conference, 1988, 147–151

[10] Forsyth D., Ponce J., Computer Vision: A Modern Approach, Prentice-Hall, London, 2003

[11] Pollefeys M., Obtaining 3D Models With Hand-held Camera, SIGGRAPH Courses, 2001

[12] Konouchine A., Gaganov V., Vezhnevets V., “Combined guided tracking and matching with adaptive track initialization”, Proc. Graphicon'05, 2005, 301–304

[13] Hartley R., Sturm P., “Triangulation”, CVIU, 68:2 (1997), 146–157 | MR

[14] Chum O., Matas J., “Randomized RANSAC with $T(d,d)$ test”, Proc. British Machine Vision Conf., 2002, 448–457

[15] Nister D., “Preemptive RANSAC for live structure and motion estimation”, Proc. ICCV'03, 2003, 199–206

[16] Chum O., Matas J., Kittler J., “Locally optimized RANSAC”, Lecture Notes in Computer Science, 2781, 2003, 236–243, Proc. 25-th Pattern Recognition Symposium (DAGM)

[17] Tordoff B., Murray D., “Guided sampling and consensus for motion estimation”, Lecture Notes in Computer Science, 2350, 2002, 82–96, Proc. ECCV'02 | Zbl