Title :
Correspondence matching based on Higher Order Statistics for Multi-view plus Depth video sequences
Author :
Colonnese, S. ; Oliveira, P. ; Rosato, A. ; Ungaro, L. ; Beghdadi, Azeddine ; Biagi, Mauro ; Scarano, G.
Author_Institution :
DIET, Univ. La Sapienza di Roma, Rome, Italy
Abstract :
This work addresses the problem of correspondence matching in multiview video sequences when co-acquired depth maps are available, as in the novel Multiview Video plus Depth (MVD) format. For the purpose of activity-based correspondence matching, we exploit the view depth information, allowing a thorough geometrical analysis of the video scene, and the statistical analysis of the inter-frame differences.
Keywords :
geometry; higher order statistics; image matching; image sequences; MVD format; correspondence matching; geometrical analysis; higher order statistics; inter-frame differences; multiview video plus depth format; multiview video sequences; statistical analysis; video scene; Cameras; Entropy; Higher order statistics; Mutual information; Noise; Support vector machine classification; Vectors; Correspondence matching; Higher Order Statistics; Multiview Video plus Depth (MVD) format;
Conference_Titel :
Visual Information Processing (EUVIP), 2014 5th European Workshop on
Conference_Location :
Paris
DOI :
10.1109/EUVIP.2014.7018404