择了一种速度、特征点数量和精度都比较好的组合方案：FAST角点检测算法+sift特征描述子+FLANN(Fast Library for Approximate Nearest Neighbors) 匹配算法。-Choose a speed and precision of the number of feature points are relatively good combination scheme: FAST corner detection algorithm+sift featur

基于VC++的双目立体视觉检测 采用SIFT特征点计算稀疏匹配 和稠密匹配-VC++ based binocular stereo vision detection using SIFT feature points to calculate sparse matching and dense matching

三维重建源码，由双目立体视觉进行三位重建。并给出了几种重建方法的介绍，如基于块匹配的三维重建、基于特征点的重建。并且给出了最终结果图像。-Three-dimensional reconstruction of the source code, the three reconstruction by binocular stereo vision. And gives several reconstruction methods, such as 3 d reconstruction based