Appearance Based Extraction of Planar Structure in Monocular SLAM

Jose Martinez Carranza, Andrew Calway

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

This work concerns the building of enhanced scene maps during real-time monocular SLAM. Specifically, we present a novel algorithm for detecting and estimating planar structure in a scene based on both appearance and geometric information. We adopt a hypothesis testing framework, in which the validity of planar patches within a triangulation of the point based scene map are assessed against an appearance metric. A key contribution is that the metric incorporates the uncertainties available within the SLAM filter through the use of a test statistic assessing error distribution against predicted covariances, hence maintaining a coherent probabilistic formulation. Experimental results indicate that the approach is effective, having good detection and discrimination properties, and leading to convincing planar feature representations.
Translated title of the contributionAppearance Based Extraction of Planar Structure in Monocular SLAM
Original languageEnglish
Title of host publicationImage Analysis
Subtitle of host publication16th Scandinavian Conference, SCIA 2009, Oslo, Norway, June 15-18, 2009. Proceedings
PublisherSpringer Berlin Heidelberg
Pages269-278
Number of pages10
ISBN (Electronic)9783642022302
ISBN (Print)9783642022296
DOIs
Publication statusPublished - 2009

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume5575
ISSN (Print)0302-9743

Bibliographical note

ISBN: 364202229403029743
Publisher: Springer
Name and Venue of Conference: 16th Scandinavian Conference on Image Analysis
Other identifier: 2001024

Fingerprint Dive into the research topics of 'Appearance Based Extraction of Planar Structure in Monocular SLAM'. Together they form a unique fingerprint.

Cite this