Logo image
Probabilistic Scene Analysis for Robust Stereo Correspondence
Conference proceeding   Peer reviewed

Probabilistic Scene Analysis for Robust Stereo Correspondence

Markus Steffens, Dominik Aufderheide, Stephan Kieneke, Werner Krybus, Christine Kohring and Danny Morton
IMAGE ANALYSIS AND RECOGNITION, PROCEEDINGS, Vol.5627, pp.697-706
Lecture Notes in Computer Science
01/01/2009

Abstract

Computer Science Computer Science, Artificial Intelligence Computer Science, Theory & Methods Imaging Science & Photographic Technology Science & Technology Technology
Most area-based approaches for stereo correspondence are leading to a large set of non-correct matches in the generated disparity-map. These are mainly caused by low textured areas, half Occlusions, discontinuities in depth and the Occurrence of repetitive patterns in the observed scene. This paper proposes a novel framework where non salient regions inside the stereo pair are identified previously to the matching, whereat the decision about the involvement of particular areas in the correspondence analysis is realized based on the fusion of separate confidence maps. They describe the possibility for a correct matching based on different criteria.

Metrics

5 Record Views
3 Times Cited - Scopus

Details

Logo image

Usage Policy