Find centralized, trusted content and collaborate around the technologies you use most.
Teams
Q&A for work
Connect and share knowledge within a single location that is structured and easy to search.
OpenCV 的 reprojectImageTo3D 应该提供来自视差图像和 Q 投影矩阵的 xyz 坐标。它返回一个 3 通道无符号字符图像 _3dImage。_3dImage(x,y) 的每个元素都包含根据视差图计算的点 (x,y) 的 3D 坐标。应该如何从图像中访问 xyz 坐标?
哦,等等,这不是三通道无符号字符图像,而是三通道浮点图像
Point3f p = _3dImage.at<Point3f>(row,col); // p.x // p.y // p.z