OpenCV Q&A Forum - RSS feedhttp://answers.opencv.org/questions/OpenCV answersenCopyright <a href="http://www.opencv.org">OpenCV foundation</a>, 2012-2018.Mon, 03 Aug 2020 02:07:24 -0500Coordinate frame transformation from NED to OpenCV convention, and the Pinhole Camera Modelhttp://answers.opencv.org/question/233204/coordinate-frame-transformation-from-ned-to-opencv-convention-and-the-pinhole-camera-model/ Hello,
I'm working on an SFM module where I have camera coordinates wrt a world coordinate system (in NED). I have the calibrated camera intrinsics matrix, and with the R,T of the camera wrt world, I compute the Projection matrix (intrinscs matrix * R|T) for each image, and camera position. However, I'm not sure if this Projection matrix is right since the R|T is in NED, and openCV uses a different convention.I'm trying to use the CV::SFM::triangulatePoints, but I'm not getting consistent results.
How will this affect the projection matrix, and is the conversion of the poses to the OpenCV frame necessary?
Sun, 02 Aug 2020 12:28:00 -0500http://answers.opencv.org/question/233204/coordinate-frame-transformation-from-ned-to-opencv-convention-and-the-pinhole-camera-model/Comment by leafdet for <p>Hello,
I'm working on an SFM module where I have camera coordinates wrt a world coordinate system (in NED). I have the calibrated camera intrinsics matrix, and with the R,T of the camera wrt world, I compute the Projection matrix (intrinscs matrix * R|T) for each image, and camera position. However, I'm not sure if this Projection matrix is right since the R|T is in NED, and openCV uses a different convention.I'm trying to use the CV::SFM::triangulatePoints, but I'm not getting consistent results.
How will this affect the projection matrix, and is the conversion of the poses to the OpenCV frame necessary?</p>
http://answers.opencv.org/question/233204/coordinate-frame-transformation-from-ned-to-opencv-convention-and-the-pinhole-camera-model/?comment=233219#post-id-233219@berak NED is the North East Down convention. It's a very commonly used convention in drones, or aerospace :).
In the Pinhole Camera Model, the camera's position has a R|T wrt some origin in the world (https://www.sciencedirect.com/topics/engineering/pinhole-camera-model)Mon, 03 Aug 2020 02:07:24 -0500http://answers.opencv.org/question/233204/coordinate-frame-transformation-from-ned-to-opencv-convention-and-the-pinhole-camera-model/?comment=233219#post-id-233219Comment by berak for <p>Hello,
I'm working on an SFM module where I have camera coordinates wrt a world coordinate system (in NED). I have the calibrated camera intrinsics matrix, and with the R,T of the camera wrt world, I compute the Projection matrix (intrinscs matrix * R|T) for each image, and camera position. However, I'm not sure if this Projection matrix is right since the R|T is in NED, and openCV uses a different convention.I'm trying to use the CV::SFM::triangulatePoints, but I'm not getting consistent results.
How will this affect the projection matrix, and is the conversion of the poses to the OpenCV frame necessary?</p>
http://answers.opencv.org/question/233204/coordinate-frame-transformation-from-ned-to-opencv-convention-and-the-pinhole-camera-model/?comment=233205#post-id-233205mind telling us, what NED is ? ;)
> with the R,T of the camera wrt world,
no such thing as a "world" here. do you mean the R,t Mat's from calibration ? they're camera <--> chessboard, and somehow useless for further svm calculationsSun, 02 Aug 2020 12:50:54 -0500http://answers.opencv.org/question/233204/coordinate-frame-transformation-from-ned-to-opencv-convention-and-the-pinhole-camera-model/?comment=233205#post-id-233205