This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
Hello,
The second image is more challenging because the chessboard is closer to a border of the image and there is too little space around the board. Moreover, the board is shadowed which make chessboard detection even more difficult.
Documentation of cv::findChessboardCorners contains a useful note regarding this situation:
The function requires white space (like a square-thick border, the wider the better) around the board to make the detection more robust in various environments. Otherwise, if there is no border and the background is dark, the outer black squares cannot be segmented properly and so the square grouping and ordering algorithm fails.
P.S. Usually 10-40 different images of a chessboard are captured to calibrate a camera accurately. Calibration with fewer number of images is too uncertain.
| | 2 | No.2 Revision |
Hello,
The second image is more challenging because the chessboard is closer to a border of the image and there is too little space around the board. Moreover, the board is shadowed which make makes chessboard detection even more difficult.
Documentation of cv::findChessboardCorners contains a useful note regarding this situation:
The function requires white space (like a square-thick border, the wider the better) around the board to make the detection more robust in various environments. Otherwise, if there is no border and the background is dark, the outer black squares cannot be segmented properly and so the square grouping and ordering algorithm fails.
P.S. Usually 10-40 different images of a chessboard are captured to calibrate a camera accurately. Calibration with fewer number of images is too uncertain.
