Morphological processing of stereoscopic image superimpositions for disparity map estimation
Abstract
This paper deals with the problem of depth map computation from a pair of rectified stereo images and presents a novel solution based on the morphological processing of disparity space volumes. The reader is guided through the four steps composing the proposed method: the segmentation of stereo images, the diffusion of superimposition costs controlled by the segmentation, the resulting generation of a sparse disparity map which finally drives the estimation of the dense disparity map. An objective evaluation of the algorithm's features and qualities is provided and is accompanied by the results obtained on Middlebury's 2014 stereo database.
Fichier principal
article_mpsv.pdf (5.67 Mo)
Télécharger le fichier
JD16_mpsv_slides.pdf (6.08 Mo)
Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...