Epipolar Geometry Estimation Using Improved LO-RANSAC
The estimation of the epipolar geometry is of great interest for a number of computer vision and robotics tasks, and which is especially difficult when the putative correspondences include a low percentage of inliers correspondences or a large subset of the inliers is consistent with a degenerate configuration of the epipolar geometry that is totally incorrect. The Random Sample Consensus (RANSAC) algorithm is a popular tool for robust estimation, primarily due to its ability to tolerate a tremendous fraction of outliers. In this paper, we propose an approach for improve of locally optimized RANSAC (LO-RANSAC) that has the benefit of offering fast and accurate RANSAC. The resulting algorithm when tested on real images with or without degenerate configurations gives quality estimations and achieves significant speedups compared to the LO-RANSAC algorithms.