AUTOMATIC COMPUTATION OF FUNDAMENTAL MATRIX TOGETHER WITH INTEREST POINTS IN CORRESPONDENCE BETWEEN TWO IMAGES

摘要：

The fundamental matrix is a basic tool in the analysis of scenes taken with two uncalibrated cameras. As was known, the corresponding cameras matrix may then be determined, up to a protective ambiguity, from the computed F, so the following actions will be continued such as reconstruction and so on. In the paper, the method for computing F from a set of corresponding image points is described, and the scale-invariant features extracting is used for computing the interest points. Experimental results show that, the method described is very exactly.

关键词： Two-View Geometry Epipolar Geometry Fundamental Matriz Feature detection L-M Algorithm RANSAC

作者: JIE ZHAO FENG YANG WEI-JING LIU

作者单位: The College of Electronic and Information Engineering, Hebei University, Baoding 071002, China

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 2805-2809

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）