Dynamic and hierarchical multi-structure geometric model fitting
Authors:
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1044-1051
Abstract
The ability to generate good model hypotheses is instrumental to accurate and robust geometric model fitting. We present a novel dynamic hypothesis generation algorithm for robust fitting of multiple structures. Underpinning our method is a fast guided sampling scheme enabled by analysing correlation of preferences induced by data and hypothesis residuals. Our method progressively accumulates evidence in the search space, and uses the information to dynamically (1) identify outliers, (2) filter unpromising hypotheses, and (3) bias the sampling for active discovery of multiple structures in the data-All achieved without sacrificing the speed associated with sampling-based methods. Our algorithm yields a disproportionately higher number of good hypotheses among the sampling outcomes, i.e., most hypotheses correspond to the genuine structures in the data. This directly supports a novel hierarchical model fitting algorithm that elicits the underlying stratified manner in which the structures are organized, allowing more meaningful results than traditional “flat” multi-structure fitting.Keywords
This publication has 13 references indexed in Scilit:
- Model Fitting with Sufficient Random Sample CoverageInternational Journal of Computer Vision, 2010
- Deterministic Sample Consensus with Multiple Match Hypotheses2010
- BLOGS: Balanced local and global search for non-degenerate two view epipolar geometry2009
- Nonlinear Mean Shift over Riemannian ManifoldsInternational Journal of Computer Vision, 2009
- Visualizing Incomplete and Partially Ranked DataIEEE Transactions on Visualization and Computer Graphics, 2008
- Nonlinear Mean Shift for Clustering over Analytic Manifolds2006
- Guided-MLESAC: faster image transform estimation by using matching priorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Matching with PROSAC — Progressive Sample Consensus2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Detection of Planar Regions with Uncalibrated Stereo using Distributions of Feature Points2004