1

I am currently using the aruco library to track fiducial markers, and I use the detect() method of the MarkerDetector class. The detect() method takes as input the camera parameters (camera matrix, distortion coefs), the length of the marker and the image. I actually use the function cv::undistort() to undistort the image before giving it as input to detect(). But i was asking myself if the detect() method already undistorts the image ? Which means that i should give the raw image as input to detect(), instead of the undistorted one. I read the doc of the function, but no information is given about that.

Thank you for your answers :-)

Christoph Rackwitz
  • 11,317
  • 4
  • 27
  • 36
Mohamed Adjel
  • 13
  • 2

1 Answers1

1

edit: I don't know the standalone library and can only talk about the aruco module of OpenCV

If you pass an undistorted picture to the aruco API, do not pass any distortion coefficients to the aruco API. You should however pass the "raw" image instead (and distortion coefficients in the following call), because that spares you from having to undistort the entire picture, which costs more than doing it to a few points.

The aruco module API was recently changed to clarify this... if I remember correctly. The detectMarkers() method is not supposed to do the undistorting, and does not do that. The undistorting, of points, is supposed to happen in the pose estimation call, estimatePoseSingleMarkers() or related ones, which comes after.

Yes, some parts of the docs are bad, and I wouldn't put all my trust in the implementation either.

Christoph Rackwitz
  • 11,317
  • 4
  • 27
  • 36
  • Yes, I can confirm that OpenCV has removed the camera matrix and distortion coefficients from `detectMarkers()`. I recently updated my OpenCV to version 4.6.0 and you no longer need these Parameters to detect markers. You only need it for the Pose estimation! I recommend upgrading to a newer version of OpenCv. – William Hoole Sep 05 '22 at 12:12
  • Tank you very much for your answers ! Sorry for the late answer. Well, i am actually using the `detect()` method of the `MarkerDetector` class of the [standalone aruco library](https://sourceforge.net/projects/aruco/) (not the one that is included as a ThirdParty library with opencv, and that uses `detectMarkers()` function). Anyway, it seems that it works way better when I use the raw image, passing the distortion coefficients to the `MarkerDetector.detect()` method. Thank you for the help ! – Mohamed Adjel Sep 07 '22 at 15:26
  • thanks for clarifying. I just assumed that you mean the OpenCV module since you also mentioned using other OpenCV functions. – Christoph Rackwitz Sep 07 '22 at 16:16