stereo-identical points

This paper proposes a practical method of automatic acquisition cognominal points in system of binocular stereo vision, which provides necessary parameter for camera relative calibration, moreover it presents farther study in acquiring and matching feature points.

提出了一种新的方法来进行双目立体视觉系统同名点的自动提取，对现有的特征点匹配方法进行了改进，通过对同名点的自动提取，获取了摄像机相对校准所必需的参数。

A new feature-point-based stereo matching algorithm is proposed in this paper, in order to match feature points more efficiently and accurately.

为了快速并更精确的对特征点进行立体匹配，本文提出了一种新的基于特征点的立体匹配算法。

It summarizes the basic knowledge, including the concept of digital images and feature points, stereo matching principle, parallax ranging principle, matching feature choice, matching constraints and geometric theory.

总结了有关特征点提取和匹配的基础知识，包括数字图像和特征点的概念、立体匹配原理、视差测距原理、匹配基元的选择、匹配约束条件以及对极几何的相关内容。

This paper presents a high-precision stereo camera calibration technique combined the improved two-step method with accurate control points, in which the lens distortion of a camera is modeled by a combination of radial distortion and tangential distortion.

给出了将改进的两步法与精确控制点相结合来精确校准立体像机的新技术，像机镜头畸变模型考虑了径向畸变和切向畸变。