2013 · 91 citations · 15 references
ComputingComputer ScienceComputer VisionMachine LearningStatistical ModelingMatching MethodsObject RecognitionPattern RecognitionCorrespondence MatchingFeature Correspondence AnalysisFeature Correspondence EstimationFeature MatchingFundamental Matrix EstimationNearest Neighbor MatchingPoint Feature MatchingRansac
Algorithms based on RANSAC that estimate models using feature correspondences between images can slow down tremendously when the percentage of correct correspondences (inliers) is small. In this paper, we present a probabilistic parametric model that allows us to assign confidence values for each matching correspondence and therefore accelerates the generation of hypothesis models for RANSAC under these conditions. Our framework leverages Extreme Value Theory to accurately model the statistics of matching scores produced by a nearest-neighbor feature matcher. Using a new algorithm based on this model, we are able to estimate accurate hypotheses with RANSAC at low inlier ratios significantly faster than previous state-of-the-art approaches, while still performing comparably when the number of inliers is large. We present results of homography and fundamental matrix estimation experiments for both SIFT and SURF matches that demonstrate that our method leads to accurate and fast model estimations.
15
Martin A. Fischler, Robert C. Bolles · Communications of the ACM · 1981 · 25.5K citations · Full text
Speeded-Up Robust Features (SURF)
Herbert Bay, Andreas Ess, Tinne Tuytelaars et al. · Computer Vision and Image Understanding · 2008 · 13.4K citations
A Comparison of Affine Region Detectors
Krystian Mikolajczyk, Tinne Tuytelaars, C. Schmid et al. · International Journal of Computer Vision · 2005 · 2.9K citations