The maximum disparity values occurring in Middlebury database are as follows: for 6 of the images, their absolute maximum disparities are less than 20 pixels (≈5% of the scene), and in the remaining 27 images, the absolute maximum disparities vary between 38 to 71 (≈10% to 16% of the scene).
These features may include, for example, the maximum disparity, disparity range, disparity energy, and other measures of the disparity distribution.
Also, Middlebury provides the maximum disparity values of each image individually.
Under fixed viewing conditions, the vergence-accommodation conflict can be related to the maximum disparity.
Prior to pooling, cylinder disparity values were normalised by the maximum disparity from the range used at each site.
Prior to pooling, we normalized stimulus disparity values at each site by dividing them by the maximum disparity value of the site.
Although these video scenes do not have ground-truth information according to which k could be set (as in Section 3.1), we have set k=80 (≈17% of the scene) manually, based on the observed maximum absolute disparity between the stereo pairs throughout the video.
The interval is denoted by dmin and dmax, which correspond to minimum and maximum disparities respectively.
This is not to say all students should be granted the same level of financial support, just that the disparity between the minimum and maximum loan should be more closely examined.
This ensured that the maximum normalized disparity was 1 and minimum was −1, with the other disparity values lying in between.
