Skip to the main content

Original scientific paper

RANSAC-Based Stereo Image Registration with Geometrically Constrained Hypothesis Generation

Robert Cupec orcid id orcid.org/0000-0003-4451-7952 ; University of Osijek, Faculty of electrical engineering, Osijek, Croatia
Emanuel Karlo Nyarko orcid id orcid.org/0000-0001-8041-3646 ; University of Osijek, Faculty of electrical engineering, Osijek, Croatia
Andreja Kitanov ; University of Zagreb, Faculty of electrical engineering and computing, Zagreb, Croatia
Ivan Petrović orcid id orcid.org/0000-0001-9961-5627 ; University of Zagreb, Faculty of electrical engineering and computing, Zagreb, Croatia


Full text: english pdf 592 Kb

page 195-204

downloads: 907

cite


Abstract

An approach for registration of sparse feature sets detected in two stereo image pairs taken from two different views is proposed. Analogously to many existing image registration approaches, our method consists of initial matching of features using local descriptors followed by a RANSAC-based procedure. The proposed approach is especially suitable for cases where there is a high percentage of false initial matches. The strategy proposed in this paper is to modify the hypothesis generation step of the basic RANSAC approach by performing a multiple-step procedure which uses geometric constraints in order to reduce the probability of false correspondences in generated hypotheses. The algorithm needs approximate information about the relative camera pose between the two views. However, the uncertainty of this information is allowed to be rather high. The presented technique is evaluated using both synthetic data and real data obtained by a stereo camera system.

Keywords

Image registration; Stereo vision; Feature tracking; RANSAC

Hrčak ID:

47493

URI

https://hrcak.srce.hr/47493

Publication date:

22.12.2009.

Article data in other languages: croatian

Visits: 2.208 *