Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting

Ming Liu

doi:10.1109/ROBIO.2014.7090597

Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting

Ming Liu^*

^*Corresponding author for this work

Department of Electronic and Computer Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

8 Citations (Scopus)

Abstract

In this paper, we introduce an efficient point-cloud segmentation algorithm, inspired by efficient segmentation (also named as super-pixel extraction). It uses parameterised 'normal words' as distance measures, which are obtained by clustering of surface normals. We estimate the surface normals by the sparse tensor voting framework, which enables adaptive structural extraction, even for the case of missing points. The output result is consist of labeled point representations regarding plane assumptions, which is validated by metrics based on information theory. We show the quality of the segmentation results by experiments on real datasets, and demonstrate its potentials in aiding 2.5D topological navigation for structured environments.

Original language	English
Title of host publication	2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1805-1810
Number of pages	6
ISBN (Electronic)	9781479973965
DOIs	https://doi.org/10.1109/ROBIO.2014.7090597
Publication status	Published - 20 Apr 2014
Event	2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014 - Bali, Indonesia Duration: 5 Dec 2014 → 10 Dec 2014

Publication series

Name	2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014

Conference

Conference	2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014
Country/Territory	Indonesia
City	Bali
Period	5/12/14 → 10/12/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Access to Document

10.1109/ROBIO.2014.7090597

Cite this

Liu, M. (2014). Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting. In 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014 (pp. 1805-1810). Article 7090597 (2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROBIO.2014.7090597

Liu, Ming. / Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting. 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1805-1810 (2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014).

@inproceedings{33296b2c93ec4f148a20dfcfff6f0617,

title = "Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting",

abstract = "In this paper, we introduce an efficient point-cloud segmentation algorithm, inspired by efficient segmentation (also named as super-pixel extraction). It uses parameterised 'normal words' as distance measures, which are obtained by clustering of surface normals. We estimate the surface normals by the sparse tensor voting framework, which enables adaptive structural extraction, even for the case of missing points. The output result is consist of labeled point representations regarding plane assumptions, which is validated by metrics based on information theory. We show the quality of the segmentation results by experiments on real datasets, and demonstrate its potentials in aiding 2.5D topological navigation for structured environments.",

author = "Ming Liu",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014 ; Conference date: 05-12-2014 Through 10-12-2014",

year = "2014",

month = apr,

day = "20",

doi = "10.1109/ROBIO.2014.7090597",

language = "English",

series = "2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014",

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

pages = "1805--1810",

booktitle = "2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014",

}

Liu, M 2014, Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting. in 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014., 7090597, 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014, Institute of Electrical and Electronics Engineers Inc., pp. 1805-1810, 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014, Bali, Indonesia, 5/12/14. https://doi.org/10.1109/ROBIO.2014.7090597

Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting. / Liu, Ming.
2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1805-1810 7090597 (2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting

AU - Liu, Ming

PY - 2014/4/20

Y1 - 2014/4/20

N2 - In this paper, we introduce an efficient point-cloud segmentation algorithm, inspired by efficient segmentation (also named as super-pixel extraction). It uses parameterised 'normal words' as distance measures, which are obtained by clustering of surface normals. We estimate the surface normals by the sparse tensor voting framework, which enables adaptive structural extraction, even for the case of missing points. The output result is consist of labeled point representations regarding plane assumptions, which is validated by metrics based on information theory. We show the quality of the segmentation results by experiments on real datasets, and demonstrate its potentials in aiding 2.5D topological navigation for structured environments.

AB - In this paper, we introduce an efficient point-cloud segmentation algorithm, inspired by efficient segmentation (also named as super-pixel extraction). It uses parameterised 'normal words' as distance measures, which are obtained by clustering of surface normals. We estimate the surface normals by the sparse tensor voting framework, which enables adaptive structural extraction, even for the case of missing points. The output result is consist of labeled point representations regarding plane assumptions, which is validated by metrics based on information theory. We show the quality of the segmentation results by experiments on real datasets, and demonstrate its potentials in aiding 2.5D topological navigation for structured environments.

UR - https://www.scopus.com/pages/publications/84949929251

U2 - 10.1109/ROBIO.2014.7090597

DO - 10.1109/ROBIO.2014.7090597

M3 - Conference Paper published in a book

AN - SCOPUS:84949929251

T3 - 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014

SP - 1805

EP - 1810

BT - 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014

Y2 - 5 December 2014 through 10 December 2014

ER -

Liu M. Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting. In 2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1805-1810. 7090597. (2014 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2014). doi: 10.1109/ROBIO.2014.7090597

Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this