Evaluation of disparity map computed using local stereo parametric and Non-Parametric methods
Tahera Tabssum, Priya Charles, Anupama V. Patil · 2016
Vision is the most important sense for humans and because of this human vision system we are able to see the 3D world around us with great clarity and are able to find out depth of each and every object. Many Active and Passive depth estimation techniques have been proposed which are capable of estimating depth of real world scene among which one of the passive method, stereo vision has been proven to provide remarkable results. In this paper different algorithms for estimating reliable and accurate correspondence match for stereoscopic image pairs is presented, which is based on correlation techniques. By taking neighboring disparity values into account, reliability and accuracy of the estimated disparity values are increased. In this paper we present a comparison between different stereo correspondence matching algorithms like SAD, SSD, NCC, Non Parametric census transform & SAD by derivatives and analyze the best match to ground truth images taken from Middlebury online dataset using RMS error and BAD PIXEL match as quality metrics.