Ask Your Question

Large number of chessboard corners and camera calibration

asked 2013-04-09 09:59:41 -0500

tomcat81 gravatar image

updated 2013-04-09 10:00:10 -0500

I am implementing camera calibration using a chessboard pattern as the test image. However, I am having problems identifying corners when I use a large number of corners (18x27 inner corners). Identifying corners works fine when I use a smaller test pattern (6x9 inner corners). I've tried adding a white border to the image but to no avail.

Is there a limit as to how many corners can be detected using the OpenCV "FindChessboardCorners" function? Is there anyway I can find the corners for a large test pattern such as 18x27 for camera calibration?

My Python script is below but I don't think there should be any problems with it:

    img = cv.LoadImage(filename,cv.CV_8UC1)
    img2 = cv.LoadImage(filename,cv.CV_LOAD_IMAGE_COLOR)
    found,corners = cv.FindChessboardCorners(img,(17,26),0)
    corners2 = cv.FindCornerSubPix(img,corners,(5,5),(-1,-1),(cv.CV_TERMCRIT_EPS,0,0.001))
edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted

answered 2013-04-09 10:05:46 -0500

My opinion is: there is no limitation on the number of corners, but the corners became small it they are too many (in pixels), therefore their is a limit on the corners size "detectable". Basically, more corners imply smaller square => more difficult to detect. Try 6x9 very small corners on a chessboard to be sure...

edit flag offensive delete link more


Basically what he said. Also add to that the fact that due to smaller amount of pixels in the actual corner, there is less "change" possible, which means that the underlying corner detector, doesn't succeed in finding the corners anymore.

StevenPuttemans gravatar imageStevenPuttemans ( 2013-04-09 12:23:46 -0500 )edit

I just tried with the 6x9 pattern and corner detection becomes unreliable with decreasing pixel size of the square. Is there an actual limit to the square pixel size in which corner detection is still reliable?

tomcat81 gravatar imagetomcat81 ( 2013-04-10 07:10:25 -0500 )edit
Login/Signup to Answer

Question Tools


Asked: 2013-04-09 09:59:41 -0500

Seen: 1,015 times

Last updated: Apr 09 '13