Publication
Efficient vision-based loop closing techniques for delayed state robot mapping
Conference Article
Conference
Frontier Science Conference Series for Young Researchers: Experimental Cognitive Robotics (FSCYR:ECR)
Edition
2008
Pages
1-6
Doc link
http://www.esf.org/conferences/08231
File
Abstract
This paper shows results on outdoor vision-based loop closing for Simultaneous Localization and Mapping. Our experiments show that for loops of over 50m, the pose estimates maintained with a Delayed-State Extended Information Filter are consistent enough to guarantee assertion of vision-based pose constraints for loop closure, provided no necessary information links are added to the estimator. The technique computes relative pose constraints via a robust least squares minimisation of 3D point correspondences, which are in turn obtained from the matching of SIFT features over candidate image pairs. We propose a loop closure test that checks both for closeness of means and for highly informative updates at the same time.
Categories
computer vision, robots.
Scientific reference
V. Ila, J. Andrade-Cetto and A. Sanfeliu. Efficient vision-based loop closing techniques for delayed state robot mapping, 2008 Frontier Science Conference Series for Young Researchers: Experimental Cognitive Robotics, 2008, Kanagawa, Japó, pp. 1-6, ESF-JSPS.
Follow us!