Advertisement
Guest User

Untitled

a guest
Mar 23rd, 2018
100
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 1.17 KB | None | 0 0
  1. I think it is because your variable calibration_flags as CALIB_CHECK_COND set.
  2. Try disabling this flag. Without it I was able to undistort your images (see links below).
  3.  
  4. I am not sure what this check is for (the [documentation][1] is not very explicit). This flag reject some images¹ of my gopro hero 3 even when the chessboard is visible and detected. In my case one image among 20 is not passing this test. This image has the chessboard close to the left border.
  5.  
  6. https://i.stack.imgur.com/m2WF6.jpg
  7. https://i.stack.imgur.com/KiTRz.jpg
  8. https://i.stack.imgur.com/MhHyN.jpg
  9. https://i.stack.imgur.com/pSiyG.jpg
  10. https://i.stack.imgur.com/drXSL.jpg
  11. https://i.stack.imgur.com/DDze1.jpg
  12. https://i.stack.imgur.com/b6l8f.jpg
  13. https://i.stack.imgur.com/9MrAk.jpg
  14. https://i.stack.imgur.com/WYmg5.jpg
  15. https://i.stack.imgur.com/rmJ5Q.jpg
  16. https://i.stack.imgur.com/K8k8Y.jpg
  17. https://i.stack.imgur.com/MiBER.jpg
  18.  
  19.  
  20. ¹ in OpenCV versions >= 3.4.1 the [error message][2] tells you which image is not passing the test
  21.  
  22.  
  23. [1]: https://docs.opencv.org/3.4.1/db/d58/group__calib3d__fisheye.html
  24. [2]: https://github.com/opencv/opencv/pull/9067/commits/5ca7dcc6e74b9c6068b8de1f49f289d6bc6b5a0b
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement