Appearance Based Extraction of Planar Structure in Monocular SLAM

Jose Martinez Carranza; Andrew Calway

doi:10.1007/978-3-642-02230-2_28

Appearance Based Extraction of Planar Structure in Monocular SLAM

Jose Martinez Carranza, Andrew Calway

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 contribution	Appearance Based Extraction of Planar Structure in Monocular SLAM
Original language	English
Title of host publication	Image Analysis
Subtitle of host publication	16th Scandinavian Conference, SCIA 2009, Oslo, Norway, June 15-18, 2009. Proceedings
Publisher	Springer Berlin Heidelberg
Pages	269-278
Number of pages	10
ISBN (Electronic)	9783642022302
ISBN (Print)	9783642022296
DOIs	https://doi.org/10.1007/978-3-642-02230-2_28
Publication status	Published - 2009

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin Heidelberg
Volume	5575
ISSN (Print)	0302-9743

Bibliographical note

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

Access to Document

10.1007/978-3-642-02230-2_28

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=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

@inproceedings{146b68ebfef647068b687ac725f98864,

title = "Appearance Based Extraction of Planar Structure in Monocular SLAM",

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. ",

author = "Carranza, {Jose Martinez} and Andrew Calway",

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

year = "2009",

doi = "10.1007/978-3-642-02230-2_28",

language = "English",

isbn = "9783642022296",

series = "Lecture Notes in Computer Science",

publisher = "Springer Berlin Heidelberg",

pages = "269--278",

booktitle = "Image Analysis",

address = "Germany",

}

Appearance Based Extraction of Planar Structure in Monocular SLAM. / Carranza, Jose Martinez; Calway, Andrew.

Image Analysis: 16th Scandinavian Conference, SCIA 2009, Oslo, Norway, June 15-18, 2009. Proceedings. Springer Berlin Heidelberg, 2009. p. 269-278 (Lecture Notes in Computer Science; Vol. 5575).

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

TY - GEN

T1 - Appearance Based Extraction of Planar Structure in Monocular SLAM

AU - Carranza, Jose Martinez

AU - Calway, Andrew

N1 - ISBN: 364202229403029743 Publisher: Springer Name and Venue of Conference: 16th Scandinavian Conference on Image Analysis Other identifier: 2001024

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-02230-2_28

DO - 10.1007/978-3-642-02230-2_28

M3 - Conference Contribution (Conference Proceeding)

SN - 9783642022296

T3 - Lecture Notes in Computer Science

SP - 269

EP - 278

BT - Image Analysis

PB - Springer Berlin Heidelberg

ER -