After camera calibration is completed , the camera parameters will be used to compute the 3d coordinates of scene points together with stereo matching results based on triangulation 在完成摄像机参数的标定以后,需要利用立体匹配结果对空间点进行三维坐标重建。本文采用一种欧氏重建算法对空间点进行三维重建,得到空间点的三维坐标。
Through stereo matching we can find image positions of identical object point in twain images . characteristic selecting , criterions determination and algorithms achieving are three important procedures 双视觉立体匹配是寻找同一目标点在两幅图像中的成像位置，匹配特征的选取、匹配准则的确定、匹配算法的实现是立体匹配的三个重要步骤。
This paper paid most efforts on the algorithms of image processing and stereo corresponding of the grid nodes concerning the special objects - grid images . some applicable algorithms are proposed or improved 本论文着重研究了针对带有网格标记的图象这个特殊的处理对象进行图象处理、立体匹配等算法的优化的问题，提出或者改进了一些可行的算法。
A stereo matching approach based on edge feature is proposed . the procedure of the correspondence is fulfilled through the edge - detection , the similarity check and the consistence check . rebuild 3d image for disperse data and achieve depth information 提出基于边缘特征的立体匹配方法，通过边缘检测、相似性检验和相容性检验完成了匹配的全过程，并对得到的离散数据进行了三维重建，恢复深度信息。
Binocular vision research is one of the most active branches of computer vision technology , including many research aspects such as camera calibration , image acquisition , feature extraction , stereo matching , depth measurement and depth information interpolation 双目视觉研究是计算机视觉研究中最为活跃的分支之一,主要包括摄像机定标、图像采集、特征提取、立体匹配、深度计算及深度信息内插六部分内容。
After this processing , we could obtain most edge pixels " corresponding pixels and maximum of disparity . in order to make up for the sparseness of edge pixels , a new matching algorithm named census is introduced , which based on neighbor pixels " correlativity 边缘特征点的稀疏造成物体深度信息的严重缺乏，为了弥补信息缺乏的不足，本文提出了在边缘点特征匹配的基础上应用census提取像素邻域特征进行立体匹配。
The integrated binocular stereo vision system generally includes image acquisition , camera calibration , features extraction stereo matching , depth recovery and depth interpolation , etc . the features extraction and the stereo matching is mainly discussed in this paper 一个完整的双目视觉系统通常可分为图像获取、摄像机标定、特征提取、立体匹配、深度恢复和深度插值等六大部分。本论文主要是图像特征提取、立体匹配这两方面的内容展开研究。
Binocular stereovision can be defined as the process of tri - dimensional reconstruction through the abstraction , identification , matching and interpretation of twain images gathered from identical objective , mostly include : video frequency trapping , camera calibration , image preprocessing , feature extraction , stereo matching and tri - dimensional reconstruction as well 双目立体视觉是通过对同一目标的两幅图像提取、识别、匹配和解释，重建三维环境信息的过程。主要包括：视频捕获、摄像机定标、图像预处理和特征提取、立体匹配以及三维重建。
A two - stages orientation of object has been developed , which is general orientation firstly , then from this orientation point expanding to search the edge of the objective region . it can ge the center of the image after extracting the image edge . this method can greatly reduce the computer quantity of the feature extract and stereo matching and then improve the speed of recognition 提出并实现了分阶段定位策略，即先宏观粗定位，然后从从该点出发向外扩张寻求目标区域的边缘轮廓，提取到图象的边缘后，再获取图象形心，该方法大大减小了特征提取和立体匹配的计算量，提高了识别速度。
Because of the overlapping of the scenes and the limitations of the stereo - matching algorithm , one can only get a few data points instead of the in - depth information of all points . therefore , interpolation becomes a very important part in 3d modeling . on the basis of a comparative study of algorithm , the algorithm of guass wavelet interpolation , which is based on delaunay triangularion , is proposed in this thesis 因为景物的相互遮挡以及立体匹配算法的限制，由图像对往往并不能恢复所有点的深度信息，而只能得到一些稀疏的数据点，所以插值成了三维建模中一个很重要的环节，本文在比较其它算法的基础上提出了一种基于delaunay三角剖分的高斯小波插值算法，该算法只有计算简单，插值效果好的优点，而且它还克服了其它算法中要定义权重和估计参数的缺点。
