Epipolar Geometry Estimation Using Improved LO-RANSAC

摘要：

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.

关键词： Computer vision epipolar geometry robust estimation

作者: Jun Zhou

作者单位: College of Computer and Information Science, Southwest University, Chongqing, P.R. China

会议类型: 国际会议

会议名称: 2011 International Conference on Advanced Material Research(ICAMR 2011)(2011年先进材料研究国际会议)

会议地点: 重庆

会议语种:英文

页码: 255-259

在线出版日期: 2011-01-21（万方平台首次上网日期，不代表论文的发表时间）