Fast RANSAC hypothesis generation for essential matrix estimation (2011)
Type of ContentConference Contributions - Published
PublisherUniversity of Canterbury. Computer Science and Software Engineering
AuthorsBotterill, T., Mills, S., Green, R.show all
The RANSAC framework is often used to estimate the relative pose of two cameras from outlier-contaminated point correspondences, via the essential matrix, however this is computationally expensive due the cost of computing essential matrices from many sets of five to seven correspondences. The leading contemporary 5-point solver (Nister, 2004) is slow because of the expensive linear algebra decompositions and polynomial solve which are required. To avoid these costs we propose to use Levenberg-Marquardt optimisation on a manifold to find a subset of the compatible essential matrices. The proposed algorithm finds essential matrices at a higher rate than closed-form approaches, and reduces the time needed to find relative poses using RANSAC by 25%. The second contribution of this paper is to apply the optimisations used in 5-point solvers to the classic 7-point algorithm. RANSAC using the optimised 7-point algorithm is considerably faster than 5-point RANSAC (unless planar point configurations are common), despite the increased number of iterations necessary.
CitationBotterill, T., Mills, S., Green, R. (2011) Fast RANSAC hypothesis generation for essential matrix estimation. Noosa, Queensland, Australia: 2011 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 5-9 Dec 2011.
This citation is automatically generated and may be unreliable. Use as a guide only.
ANZSRC Fields of Research01 - Mathematical Sciences::0101 - Pure Mathematics::010101 - Algebra and Number Theory
08 - Information and Computing Sciences::0802 - Computation Theory and Mathematics::080201 - Analysis of Algorithms and Complexity
08 - Information and Computing Sciences::0801 - Artificial Intelligence and Image Processing::080104 - Computer Vision