从立体声对中的点Opencv 3D [英] Opencv 3D from points in stereo pair

问题描述

在OpenCV中是否有一个简单的功能来从立体相机对中获取物体的3D位置和姿势？

Is there a simple function in OpenCV to get the 3D position and pose of an object from a stereo camera pair?

我将相机和基线校准为棋盘。我现在想要获取像同一个棋盘这样的已知对象，在其自己的坐标中找到已知的3D点并找到真实世界位置（在相机坐标中）。

I have the cameras and baseline calibrated with the chess board. I now want to take a known object like the same chessboard, with known 3D points in it's own coordinates and find the real world position (in the camera coordinates).

那里是为单个相机（POSIT）执行此操作的功能，并且用于查找整个场景的3D视差图像。

There are functions to do this for a single camera (POSIT) and functions to find the 3D disparity image for the entire scene.

执行几乎相同的过程必须简单至于相机校准并找到相机对中的棋盘 - 但我找不到任何带有物体+图像坐标的功能并返回相机的立体声对。

It must be simple to do almost the same process as for the camera calibration and find the chessboard in the camera pair - but I can't find any function that takes object + image coords and returns camera coords for a stereo pair.

谢谢

推荐答案

校准完立体摄像机系统后，你得到了相对姿势（=平移+方向）两个相机。使用 solvePnP / solvePnPRansac 如果你发现其中一个摄像机和物体之间的相对姿势，那么你就得到了亲戚在物体和另一个相机之间摆姿势。例如，在用于机器人导航的立体系统中，通常从先前帧重建的3D点仅与一个相机匹配，然后估计来自3d点的相对相机姿势。立体声系统只是简化并提高了三角测量/结构重建的质量。

After calibrating your stereo camera system, you have got the relative pose (=translation+orientation) between the two cameras. Using solvePnP/solvePnPRansac if you find the relative pose between one of the cameras and the object and then consequently you have got the relative pose between the object and the other camera as well. For example, in stereo systems used for robot navigation usually reconstructed 3D points from previous frames are matched against only one of the cameras and then the relative camera pose from the 3d points is estimated. The stereo system just eases and improves the quality of triangulation/structure reconstruction.

这篇关于从立体声对中的点Opencv 3D的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！