Using Multiple Disparity Hypotheses for Improved Indoor Stereo - Robotics Institute Carnegie Mellon University

Using Multiple Disparity Hypotheses for Improved Indoor Stereo

Cristian Dima and Simon Lacroix
Conference Paper, Proceedings of (ICRA) International Conference on Robotics and Automation, Vol. 4, pp. 3347 - 3353, May, 2002

Abstract

This paper describes the design and implementation of an algorithm for improving the performance of stereo vision in environments presenting repetitive patterns or regions with relatively weak texture. The proposed algorithm makes use of the common assumption that the disparities corresponding to continuous surfaces in the world vary smoothly; we are using this assumption to alleviate the correspondence problem for pixels that cannot be reliably matched by the stereo algorithm. Our approach can be described as a reliability based filtering of the disparity image followed by a recursive propagation step. It can be applied to the output of almost any "standard" stereo algorithm with minimal modifications, and is computationally efficient.

Notes
This publication is based on work performed at LAAS-CNRS in Toulouse, France (June-August 2001).

BibTeX

@conference{Dima-2002-8463,
author = {Cristian Dima and Simon Lacroix},
title = {Using Multiple Disparity Hypotheses for Improved Indoor Stereo},
booktitle = {Proceedings of (ICRA) International Conference on Robotics and Automation},
year = {2002},
month = {May},
volume = {4},
pages = {3347 - 3353},
publisher = {IEEE},
keywords = {indoor stereo vision},
}