opencv 函数triangulatePoints（）：Reconstructs points by triangulation

最新推荐文章于 2025-01-20 13:35:42 发布

JoannaJuanCV

最新推荐文章于 2025-01-20 13:35:42 发布

阅读量5.6k

点赞数 1

分类专栏：立体视觉 SLAM学习

本文链接：https://blog.youkuaiyun.com/zfjBIT/article/details/95972477

版权

立体视觉同时被 2 个专栏收录

98 篇文章 ¥19.90 ¥99.00

订阅专栏

超级会员免费看

SLAM学习

28 篇文章

订阅专栏

OpenCV的triangulatePoints函数用于通过两个相机的投影矩阵和对应特征点，重建3D点的齐次坐标。它接受3x4的相机投影矩阵和2D特征点作为输入，输出4D的3D点坐标。注意，输出的3D坐标需要除以第四个维度以获取非齐次坐标，并且可以使用该函数计算重投影误差，辅助评估立体匹配的精度。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

C++: void triangulatePoints(InputArray projMatr1, InputArray projMatr2, InputArray projPoints1, InputArray projPoints2, OutputArray points4D)

Python: cv2.triangulatePoints(projMatr1, projMatr2, projPoints1, projPoints2[, points4D]) → points4D

C: void cvTriangulatePoints(CvMat* projMatr1, CvMat* projMatr2, CvMat* projPoints1, CvMat* projPoints2, CvMat* points4D)

Parameters:

projMatr1 – 3x4 projection matrix of the first camera.
projMatr2 – 3x4 projection matrix of the second camera.
projPoints1 – 2xN array of feature points in the first image. In case of c++ version it can be also a vector of feature points or two-channel matrix of size 1xN or Nx1.
projPoints2 – 2xN array of corresponding points in the se