I have a stereo pair, photo 1: http://savepic.org/1671682.jpg photo 2: http://savepic.org/1667586.jpg
Each image has a coordinate system. How to find the coordinates of point A in this system using the OpenCV library. It would be nice to see some sample code. I searched for it on opencv.willowgarage.com/documentation/cpp/camera_calibration_and_3d_reconstruction.html but could not find (or did not understand :))
Your stereo images are fine. What you have already done solves the correspondence problem: in both images you indicated the points “A”. This means that you know which pixel corresponds to each marking point “A”.
What you want to do is triangulate where your camera is. You can only do this by calibrating the camera. This is already inside OpenCV. http://docs.opencv.org/doc/tutorials/calib3d/camera_calibration/camera_calibration.html http://docs.opencv.org/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html
This gives you the exact vector / beam of light for each vector and the optical center of your cameras through which the beam passes. In addition, you need stereo calibration. This sets the orientation and position of each camera with respect to each other.
, "A".
, 2 2 . - 3D-.
, ( 3D), . opencv- triangulatePoints(), , A.
-, . 60% -80%, , . BASE, - , .
-, , OpenCV
http://en.wikipedia.org/wiki/Camera_resectioning
http://en.wikipedia.org/wiki/Collinearity_equation
.
, opencv book - . , .