Skip to Main content Skip to Navigation
Reports

Stereo Correspondence Through Feature Grouping and Maximal Cliques

Abstract : In this paper we propose a method to solve the stereo correspondence problem. The method matches features and feature relationships and can be paraphrased as follows. Linear edge segments are extracted from both the left and right images. Each such segment is characterized by its position and orientation in the image as well as its relationship with the nearby segments. A relational graph is thus built from each image. For each segment in one image a set of potential assignments in the other image is determined. These assignments are represented as nodes in a correspondence graph. Arcs in this graph represent compatible assignments established on the basis of segment relationships. Stereo matching becomes equivalent to searching for sets of mutually compatible nodes in this graph. These sets are found by looking for maximal cliques. The maximal clique the best suited to represent a stereo correspondence is selected using a benefit function. Finally we show numerous results obtained with this method.
Document type :
Reports
Complete list of metadata

https://hal.inria.fr/inria-00589988
Contributor : Team Perception Connect in order to contact the contributor
Submitted on : Tuesday, May 3, 2011 - 8:28:41 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM

Identifiers

  • HAL Id : inria-00589988, version 1

Collections

CEA | IMAG | CNRS | INRIA | DRT | LARA | LETI | CEA-GRE | UGA

Citation

Thomas Skordas, Radu Horaud. Stereo Correspondence Through Feature Grouping and Maximal Cliques. [Technical Report] 1987. ⟨inria-00589988⟩

Share

Metrics

Record views

213