Epipolar geometry estimated using the matches from the calibration apparatus

If we use the matched points of the calibration apparatus to compute the fundamental matrix, as you can try here, the result is much more reasonable than that obtained with the classical calibration terchnique. However, if you click on a point in the background, you will find that the epipolar line does not go through the corresponding point in the other image. The estimated fundamental matrix is available HERE, which can be computed either by image-matching or FMatrix.

What follows is Java applet which illustrates the estimated epipolar geometry. By clicking in one of the two images, the corresponding epipolar line of this point in the other image will be shown. (For better visualization, you'd better to enlarge the height of your browser such that both images are visible simultaneously.)

If you see this text, then your browser might not support Java.



Author: Zhengyou Zhang
Email: zzhang@sophia.inria.fr
Last modified: Wed Oct 23 13:46:54 MET DST