| 一个基本矩阵的鲁棒估计算法 |
| |
| 引用本文： | 郭继东,向辉.一个基本矩阵的鲁棒估计算法[J].计算机应用,2005,25(12):2845-2848. |
| |
| 作者姓名： | 郭继东 向辉 |
| |
| 作者单位： | 1. 山东经济学院,信息管理学院,山东,济南,250014
2. 山东大学,计算机科学与技术系,山东,济南,250013 |
| |
| 摘 要： | 通过分析基本矩阵的鲁棒估计方法的特点，提出了三点改进：在RANSAC（RANdom SAmpling Consensus）方法中采用了极小化再投影误差判别数据点的类别；给出再投影误差的一阶近似算法；由求出的基本矩阵和局内点数据采用LM算法对结果过一步求精，给出更好的基本矩阵估计值，使得再投影误差进一步减小，避免结果趋于局部极值。合成数据和真实图像实验均证明了该方法的有效性和可靠性。
|
| 关 键 词： | 基本矩阵 再投影误差 LM算法 RANSAC方法 |
| 文章编号： | 1001-9081（2005）12-2845-04 |
| 收稿时间： | 2005-06-26 |
| 修稿时间： | 2005-06-262005-09-01 |
Robust method for estimating the fundamental matrix |
| |
| GUO Ji-dong,XIANG Hui.Robust method for estimating the fundamental matrix[J].journal of Computer Applications,2005,25(12):2845-2848. |
| |
| Authors: | GUO Ji-dong XIANG Hui |
| |
| Affiliation: | 1. Department of Information Management, Shandong Economic University, Jinan Shandong 250014, China; 2. School of Computer Science and Technology, Shandong University, Jinan Shandong 250013, China |
| |
| Abstract: | After analyzing the characteristics of methods for computing fundamental matrix,a method was presented for robustly estimating fundamental matrix with three improvement.The data set was discriminated into inliers or outliers by minimizing reprojection error.The computation of one order approximation for reprojection error was given.To avoid local minimum,LM algorithm was adopted in last steps of RANSAC(RANdom SAmpling Consensus) algorithm.A very good estimation of fundamental matrix was obtained and the reprojection error was smaller.Experiment results on synthetic and real images demonstrated that the new algorithm is valid and robust. |
| |
| Keywords: | fundamental matrix reprojection error LM algorithm RANSAC(RANdom SAmpling Consensus) algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
|
