Precise Subpixel Disparity Measurement From Very Narrow Baseline Stereo

Abstract

To obtain depth-from-stereo imagery, it is traditionally required that the baseline separation between images (or the base-to-height ratio) be very large in order to ensure the largest image disparity range for effective measurement. Typically, a <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</i> / <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> ratio in the range of 0.6-1 is preferred. As a consequence, most existing stereo-matching algorithms are designed to measure disparities reliably with only integer-pixel precision. However, wide baselines may increase the possibility of occlusion occurring between highly contrasting relief, imposing a serious problem to digital elevation model (DEM) generation in urban and highly dissected mountainous areas. A narrow-baseline stereo configuration can alleviate the problem significantly but requires very precise measurements of disparity at subpixel levels. In this paper, we demonstrate a stereo-matching algorithm, based upon the robust <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">phase correlation</i> method, that is capable of directly measuring disparities up to 1/50th pixel accuracy and precision. The algorithm enables complete and dense surface shape information to be retrieved from images with unconventionally low <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</i> / <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</i> ratios (e.g., less than 0.01), potentially allowing DEM generation from images that would otherwise not be deemed suitable for the purpose.