3D point cloud segmentation using topological persistence

William J. Beksi; Nikolaos Papanikolopoulos

doi:10.1109/ICRA.2016.7487710

3D point cloud segmentation using topological persistence

William J. Beksi, Nikolaos Papanikolopoulos

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Scopus citations

Abstract

In this paper, we present an approach to segment 3D point cloud data using ideas from persistent homology theory. The proposed algorithms first generate a simplicial complex representation of the point cloud dataset. Next, we compute the zeroth homology group of the complex which corresponds to the number of connected components. Finally, we extract the clusters of each connected component in the dataset. We show that this technique has several advantages over state of the art methods such as the ability to provide a stable segmentation of point cloud data under noisy or poor sampling conditions and its independence of a fixed distance metric.

Original language	English (US)
Title of host publication	2016 IEEE International Conference on Robotics and Automation, ICRA 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5046-5051
Number of pages	6
ISBN (Electronic)	9781467380263
DOIs	https://doi.org/10.1109/ICRA.2016.7487710
State	Published - Jun 8 2016
Event	2016 IEEE International Conference on Robotics and Automation, ICRA 2016 - Stockholm, Sweden Duration: May 16 2016 → May 21 2016

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
Volume	2016-June
ISSN (Print)	1050-4729

Other

Other	2016 IEEE International Conference on Robotics and Automation, ICRA 2016
Country/Territory	Sweden
City	Stockholm
Period	5/16/16 → 5/21/16

Bibliographical note

Funding Information:
This material is based upon work supported by the National Science Foundation through grants #IIP-0934327, #IIS-1017344, #IIP-1332133, #IIS-1427014, #IIP-1432957, #OISE-1551059, #CNS-1514626, #CNS-1531330, and #CNS-1544887

Publisher Copyright:
© 2016 IEEE.

Copyright:
Copyright 2016 Elsevier B.V., All rights reserved.

Publisher link

10.1109/ICRA.2016.7487710

Find It

Find It at U of M Libraries

Cite this

Beksi, W. J., & Papanikolopoulos, N. (2016). 3D point cloud segmentation using topological persistence. In 2016 IEEE International Conference on Robotics and Automation, ICRA 2016 (pp. 5046-5051). Article 7487710 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2016-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2016.7487710

3D point cloud segmentation using topological persistence. / Beksi, William J.; Papanikolopoulos, Nikolaos.
2016 IEEE International Conference on Robotics and Automation, ICRA 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 5046-5051 7487710 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2016-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Beksi, WJ & Papanikolopoulos, N 2016, 3D point cloud segmentation using topological persistence. in 2016 IEEE International Conference on Robotics and Automation, ICRA 2016., 7487710, Proceedings - IEEE International Conference on Robotics and Automation, vol. 2016-June, Institute of Electrical and Electronics Engineers Inc., pp. 5046-5051, 2016 IEEE International Conference on Robotics and Automation, ICRA 2016, Stockholm, Sweden, 5/16/16. https://doi.org/10.1109/ICRA.2016.7487710

@inproceedings{8d853539fa5f4c5a8cbb6c6562e7d1de,

title = "3D point cloud segmentation using topological persistence",

abstract = "In this paper, we present an approach to segment 3D point cloud data using ideas from persistent homology theory. The proposed algorithms first generate a simplicial complex representation of the point cloud dataset. Next, we compute the zeroth homology group of the complex which corresponds to the number of connected components. Finally, we extract the clusters of each connected component in the dataset. We show that this technique has several advantages over state of the art methods such as the ability to provide a stable segmentation of point cloud data under noisy or poor sampling conditions and its independence of a fixed distance metric.",

author = "Beksi, {William J.} and Nikolaos Papanikolopoulos",

note = "Funding Information: This material is based upon work supported by the National Science Foundation through grants #IIP-0934327, #IIS-1017344, #IIP-1332133, #IIS-1427014, #IIP-1432957, #OISE-1551059, #CNS-1514626, #CNS-1531330, and #CNS-1544887 Publisher Copyright: {\textcopyright} 2016 IEEE. Copyright: Copyright 2016 Elsevier B.V., All rights reserved.; 2016 IEEE International Conference on Robotics and Automation, ICRA 2016 ; Conference date: 16-05-2016 Through 21-05-2016",

year = "2016",

month = jun,

day = "8",

doi = "10.1109/ICRA.2016.7487710",

language = "English (US)",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5046--5051",

booktitle = "2016 IEEE International Conference on Robotics and Automation, ICRA 2016",

}

TY - GEN

T1 - 3D point cloud segmentation using topological persistence

AU - Beksi, William J.

AU - Papanikolopoulos, Nikolaos

N1 - Funding Information: This material is based upon work supported by the National Science Foundation through grants #IIP-0934327, #IIS-1017344, #IIP-1332133, #IIS-1427014, #IIP-1432957, #OISE-1551059, #CNS-1514626, #CNS-1531330, and #CNS-1544887 Publisher Copyright: © 2016 IEEE. Copyright: Copyright 2016 Elsevier B.V., All rights reserved.

PY - 2016/6/8

Y1 - 2016/6/8

N2 - In this paper, we present an approach to segment 3D point cloud data using ideas from persistent homology theory. The proposed algorithms first generate a simplicial complex representation of the point cloud dataset. Next, we compute the zeroth homology group of the complex which corresponds to the number of connected components. Finally, we extract the clusters of each connected component in the dataset. We show that this technique has several advantages over state of the art methods such as the ability to provide a stable segmentation of point cloud data under noisy or poor sampling conditions and its independence of a fixed distance metric.

AB - In this paper, we present an approach to segment 3D point cloud data using ideas from persistent homology theory. The proposed algorithms first generate a simplicial complex representation of the point cloud dataset. Next, we compute the zeroth homology group of the complex which corresponds to the number of connected components. Finally, we extract the clusters of each connected component in the dataset. We show that this technique has several advantages over state of the art methods such as the ability to provide a stable segmentation of point cloud data under noisy or poor sampling conditions and its independence of a fixed distance metric.

UR - http://www.scopus.com/inward/record.url?scp=84977572004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977572004&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2016.7487710

DO - 10.1109/ICRA.2016.7487710

M3 - Conference contribution

AN - SCOPUS:84977572004

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 5046

EP - 5051

BT - 2016 IEEE International Conference on Robotics and Automation, ICRA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE International Conference on Robotics and Automation, ICRA 2016

Y2 - 16 May 2016 through 21 May 2016

ER -

3D point cloud segmentation using topological persistence

Abstract

Publication series

Other

Bibliographical note

Publisher link

Find It

Other files and links

Fingerprint

Cite this