RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets

Shuda Li; Andrew D Calway

doi:10.1109/ICRA.2015.7140094

RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets

Shuda Li, Andrew D Calway

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

17 Citations (Scopus)

1085 Downloads (Pure)

Abstract

We describe a novel RGBD relocalisation algorithm based on key point matching. It combines two com- ponents. First, a graph matching algorithm which takes into account the pairwise 3-D geometry amongst the key points, giving robust relocalisation. Second, a point selection process which provides an even distribution of the ‘most matchable’ points across the scene based on non-maximum suppression within voxels of a volumetric grid. This ensures a bounded set of matchable key points which enables tractable and scalable graph matching at frame rate. We present evaluations using a public dataset and our own more difficult dataset containing large pose changes, fast motion and non-stationary objects. It is shown that the method significantly out performs state-of-the-art methods.

Original language	English
Title of host publication	2015 IEEE International Conference on Robotics and Automation (ICRA 2015)
Subtitle of host publication	Proceedings of a meeting held 26-30 May 2015, Seattle, Washington, US
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	6374-6379
Number of pages	6
ISBN (Electronic)	9781479969234
ISBN (Print)	9781479969241
DOIs	https://doi.org/10.1109/ICRA.2015.7140094
Publication status	Published - Aug 2015
Event	2015 IEEE International Conference on Robotics and Automation - Washington, Seattle, United States Duration: 26 May 2015 → 30 May 2015

Publication series

Name	Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)	1050-4729

Conference

Conference	2015 IEEE International Conference on Robotics and Automation
Country/Territory	United States
City	Seattle
Period	26/05/15 → 30/05/15

Keywords

computer vision
robotics
SLAM
delocalisation

Access to Document

10.1109/ICRA.2015.7140094

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7140094. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 2.67 MB

Handle.net

Persistent link

Professor Andrew Calway
- Andrew.Calwaybristol.acuk
- School of Computer Science - Professor of Computer Vision
- Visual Information Laboratory
Person: Academic , Member

Cite this

Li, S., & Calway, A. D. (2015). RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets. In 2015 IEEE International Conference on Robotics and Automation (ICRA 2015): Proceedings of a meeting held 26-30 May 2015, Seattle, Washington, US (pp. 6374-6379). (Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) ). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICRA.2015.7140094

Li, Shuda ; Calway, Andrew D. / RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets. 2015 IEEE International Conference on Robotics and Automation (ICRA 2015): Proceedings of a meeting held 26-30 May 2015, Seattle, Washington, US. Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 6374-6379 (Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) ).

@inproceedings{b2544140830043198b358a0b0e9b02bb,

title = "RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets",

abstract = "We describe a novel RGBD relocalisation algorithm based on key point matching. It combines two com- ponents. First, a graph matching algorithm which takes into account the pairwise 3-D geometry amongst the key points, giving robust relocalisation. Second, a point selection process which provides an even distribution of the {\textquoteleft}most matchable{\textquoteright} points across the scene based on non-maximum suppression within voxels of a volumetric grid. This ensures a bounded set of matchable key points which enables tractable and scalable graph matching at frame rate. We present evaluations using a public dataset and our own more difficult dataset containing large pose changes, fast motion and non-stationary objects. It is shown that the method significantly out performs state-of-the-art methods.",

keywords = "computer vision, robotics, SLAM, delocalisation",

author = "Shuda Li and Calway, {Andrew D}",

year = "2015",

month = aug,

doi = "10.1109/ICRA.2015.7140094",

language = "English",

isbn = "9781479969241",

series = "Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) ",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "6374--6379",

booktitle = "2015 IEEE International Conference on Robotics and Automation (ICRA 2015)",

address = "United States",

note = "2015 IEEE International Conference on Robotics and Automation ; Conference date: 26-05-2015 Through 30-05-2015",

}

Li, S & Calway, AD 2015, RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets. in 2015 IEEE International Conference on Robotics and Automation (ICRA 2015): Proceedings of a meeting held 26-30 May 2015, Seattle, Washington, US. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) , Institute of Electrical and Electronics Engineers (IEEE), pp. 6374-6379, 2015 IEEE International Conference on Robotics and Automation, Seattle, United States, 26/05/15. https://doi.org/10.1109/ICRA.2015.7140094

RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets. / Li, Shuda; Calway, Andrew D.
2015 IEEE International Conference on Robotics and Automation (ICRA 2015): Proceedings of a meeting held 26-30 May 2015, Seattle, Washington, US. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 6374-6379 (Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) ).

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

TY - GEN

T1 - RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets

AU - Li, Shuda

AU - Calway, Andrew D

PY - 2015/8

Y1 - 2015/8

N2 - We describe a novel RGBD relocalisation algorithm based on key point matching. It combines two com- ponents. First, a graph matching algorithm which takes into account the pairwise 3-D geometry amongst the key points, giving robust relocalisation. Second, a point selection process which provides an even distribution of the ‘most matchable’ points across the scene based on non-maximum suppression within voxels of a volumetric grid. This ensures a bounded set of matchable key points which enables tractable and scalable graph matching at frame rate. We present evaluations using a public dataset and our own more difficult dataset containing large pose changes, fast motion and non-stationary objects. It is shown that the method significantly out performs state-of-the-art methods.

AB - We describe a novel RGBD relocalisation algorithm based on key point matching. It combines two com- ponents. First, a graph matching algorithm which takes into account the pairwise 3-D geometry amongst the key points, giving robust relocalisation. Second, a point selection process which provides an even distribution of the ‘most matchable’ points across the scene based on non-maximum suppression within voxels of a volumetric grid. This ensures a bounded set of matchable key points which enables tractable and scalable graph matching at frame rate. We present evaluations using a public dataset and our own more difficult dataset containing large pose changes, fast motion and non-stationary objects. It is shown that the method significantly out performs state-of-the-art methods.

KW - computer vision

KW - robotics

KW - SLAM

KW - delocalisation

U2 - 10.1109/ICRA.2015.7140094

DO - 10.1109/ICRA.2015.7140094

M3 - Conference Contribution (Conference Proceeding)

SN - 9781479969241

T3 - Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)

SP - 6374

EP - 6379

BT - 2015 IEEE International Conference on Robotics and Automation (ICRA 2015)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2015 IEEE International Conference on Robotics and Automation

Y2 - 26 May 2015 through 30 May 2015

ER -

Li S, Calway AD. RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets. In 2015 IEEE International Conference on Robotics and Automation (ICRA 2015): Proceedings of a meeting held 26-30 May 2015, Seattle, Washington, US. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 6374-6379. (Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) ). Epub 2015 May 26. doi: 10.1109/ICRA.2015.7140094

RGBD Relocalisation Using Pairwise Geometry and Concise Key Point Sets

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Profiles

Professor Andrew Calway

Cite this