文件名称:Ransac
介绍说明－－下载内容均来自于网络，请自行研究使用
RANSAC为RANdom SAmple Consensus的缩写，它是根据一组包含异常数据的样本数据集，计算出数据的数学模型参数，得到有效样本数据的算法。它于1981年由Fischler和Bolles最先提出[1]。
RANSAC算法经常用于计算机视觉中。例如，在立体视觉领域中同时解决一对相机的匹配点问题及基本矩阵的计算。
RANSAC算法的基本假设是样本中包含正确数据(inliers，可以被模型描述的数据)，也包含异常数据(Outliers，偏离正常范围很远、无法适应数学模型的数据)，即数据集中含有噪声。这些异常数据可能是由于错误的测量、错误的假设、错误的计算等产生的。同时RANSAC也假设，给定一组正确的数据，存在可以计算出符合这些数据的模型参数的方法。-RANSAC for RANdom SAmple Consensus, it is based on a set of sample data sets contain abnormal data, mathematical model parameters calculated data, the effective sample data algorithm. First proposed by Fischler and Bolles in 1981 [1]. The RANSAC algorithm often used in computer vision. For example, while addressing the three-dimensional visual field on the camera match point problem and the fundamental matrix calculation. The RANSAC algorithm' s basic assumption is that sample contains the correct data (inliers, can be described by the model data) also contain abnormal data (Outliers, deviated from the normal range very far, unable to adapt to the mathematical model of the data), that the data set contains noise. These abnormal data may be generated due to wrong measurements, wrong assumptions, wrong calculation. Simultaneously RANSAC also assume, given a set of correct data, there can be calculated out of these data to the model parameters.
RANSAC算法经常用于计算机视觉中。例如，在立体视觉领域中同时解决一对相机的匹配点问题及基本矩阵的计算。
RANSAC算法的基本假设是样本中包含正确数据(inliers，可以被模型描述的数据)，也包含异常数据(Outliers，偏离正常范围很远、无法适应数学模型的数据)，即数据集中含有噪声。这些异常数据可能是由于错误的测量、错误的假设、错误的计算等产生的。同时RANSAC也假设，给定一组正确的数据，存在可以计算出符合这些数据的模型参数的方法。-RANSAC for RANdom SAmple Consensus, it is based on a set of sample data sets contain abnormal data, mathematical model parameters calculated data, the effective sample data algorithm. First proposed by Fischler and Bolles in 1981 [1]. The RANSAC algorithm often used in computer vision. For example, while addressing the three-dimensional visual field on the camera match point problem and the fundamental matrix calculation. The RANSAC algorithm' s basic assumption is that sample contains the correct data (inliers, can be described by the model data) also contain abnormal data (Outliers, deviated from the normal range very far, unable to adapt to the mathematical model of the data), that the data set contains noise. These abnormal data may be generated due to wrong measurements, wrong assumptions, wrong calculation. Simultaneously RANSAC also assume, given a set of correct data, there can be calculated out of these data to the model parameters.
(系统自动生成,下载前可以参看下载内容)