IMPSAC: Synthesis of importance sampling and random sample consensus

Torr, Philip H. S.; Davidson, Charles E.

doi:10.1109/tpami.2003.1182098

Cited by 90 publications

(33 citation statements)

References 46 publications

(54 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A measure of inconsistency is normally the error residue of the sample in question with respect to the model. Methods in this approach include Hough transform (Ballard 1981), least median estimators (Rousseeuw 1984), and random sample consensus (RANSAC) (Fischler and Bolles 1981;Stewart 1995;Torr and Davidson 2003;Rousseeuw 1984;Wang and Suter 2004;Schindler and Suter 2005;Frahm and Pollefeys 2006).…”

Section: Relations To Previous Workmentioning

confidence: 99%

“…Particularly, a series of work has been proposed to extend RANSAC from single motions (Torr 1998;Torr and Zisserman 2000;Torr and Davidson 2003) to mixture rigid-body and homography motions (Bartoli 2001;Tong et al 2004;Schindler and Suter 2005;Subbarao and Meer 2006). On the other hand, due to the lack of a global representation for mixture motions, most algorithms have to iteratively estimate individual motions from the data set when a mixture of multiple motions is present in a common scene.…”

Section: Relations To Previous Workmentioning

confidence: 99%

“…We compare the performance of RAS with four other methods: a greedy agglomerative approach to subspace segmentation called agglomerative lossy compression (ALC) (Rao et al 2008), a form of RANSAC that finds motion models one at a time (MLESAC) (Torr and Davidson 2003), a form of RANSAC that globally finds multiple motion models via Monte-Carlo sampling (MC-RANSAC) (Schindler and Suter 2005), and the projection-based Mestimators (pbM) (Subbarao and Meer 2006). All implementations of the algorithms were obtained from their respective authors.…”

Section: Simulationmentioning

confidence: 99%

See 2 more Smart Citations

Robust Algebraic Segmentation of Mixed Rigid-Body and Planar Motions from Two Views

et al. 2010

View full text Add to dashboard Cite

This paper studies segmentation of multiple rigidbody motions in a 3-D dynamic scene under perspective camera projection. We consider dynamic scenes that contain both 3-D rigid-body structures and 2-D planar structures. Based on the well-known epipolar and homography constraints between two views, we propose a hybrid perspective constraint (HPC) to unify the representation of rigidbody and planar motions. Given a mixture of K hybrid perspective constraints, we propose an algebraic process to partition image correspondences to the individual 3-D motions, called Robust Algebraic Segmentation (RAS). Particularly, we prove that the joint distribution of image correspondences is uniquely determined by a set of (2K)-th degree polynomials, a global signature for the union of K motions of possibly mixed type. The first and second deriva- tives of these polynomials provide a means to recover the association of the individual image samples to their respective motions. Finally, using robust statistics, we show that the polynomials can be robustly estimated in the presence of moderate image noise and outliers. We conduct extensive simulations and real experiments to validate the performance of the new algorithm. The results demonstrate that RAS achieves notably higher accuracy than most existing robust motion-segmentation methods, including random sample consensus (RANSAC) and its variations. The implementation of the algorithm is also two to three times faster than the existing methods. The implementation of the algorithm and the benchmark scripts are available at http:// perception.csl.illinois.edu/ras/.

show abstract

Section: Relations To Previous Workmentioning

confidence: 99%

Section: Relations To Previous Workmentioning

confidence: 99%

Section: Simulationmentioning

confidence: 99%

See 1 more Smart Citation

Robust Algebraic Segmentation of Mixed Rigid-Body and Planar Motions from Two Views

et al. 2010

View full text Add to dashboard Cite

show abstract

“…A prototype algorithm of this class is RANSAC [8], and the many variants that have been proposed to improve its efficiency [5,6,19], and robustness [16,21,20]. Our work can be interpreted as a way to make RANSAC work in a causal fashion.…”

Section: Related Workmentioning

confidence: 99%

KALMANSAC: robust filtering by consensus

Vedaldi¹,

Jin

Favaro

et al. 2005

Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1

View full text Add to dashboard Cite

We propose an algorithm to perform causal inference of the state of a dynamical model when the measurements are corrupted by outliers. While the optimal (maximumlikelihood) solution has doubly exponential complexity due to the combinatorial explosion of possible choices of inliers, we exploit the structure of the problem to design a samplingbased algorithm that has constant complexity. We derive our algorithm from the equations of the optimal filter, which makes our approximation explicit. Our work is motivated by real-time tracking and the estimation of structure from motion (SFM). We test our algorithm for on-line outlier rejection both for tracking and for SFM. We show that our approach can tolerate a large proportion of outliers, whereas previous causal robust statistical inference methods failed with less than half as many. Our work can be thought of as the extension of random sample consensus algorithms to dynamic data, or as the implementation of pseudo-Bayesian filtering algorithms in a sampling framework.

show abstract

“…Isard et al [12] presented an approach (ICondesation) to combine low-level and high-level information by importance resampling with a particle filter. Our most related work is Torr and Davidson's research [19] on structure from motion by hybrid sampling (IMPSAC). They built a hierarchical sampling architecture with a RANSAC-MCMC estimator at the coarse level and a SIR-MCMC estimator at the finer levels.…”

Section: Related Workmentioning

confidence: 99%