Robust-PCA-based hierarchical plane extraction for application to geometric 3D indoor mapping

Suyong Yeon, Changhyun Jun, Hyunga Choi, Jaehyeon Kang, Youngmok Yun, Nakju Doh

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Purpose - The authors aim to propose a novel plane extraction algorithm for geometric 3D indoor mapping with range scan data. Design/methodology/approach - The proposed method utilizes a divide-and-conquer step to efficiently handle huge amounts of point clouds not in a whole group, but in forms of separate sub-groups with similar plane parameters. This method adopts robust principal component analysis to enhance estimation accuracy. Findings - Experimental results verify that the method not only shows enhanced performance in the plane extraction, but also broadens the domain of interest of the plane registration to an information-poor environment (such as simple indoor corridors), while the previous method only adequately works in an information-rich environment (such as a space with many features). Originality/value - The proposed algorithm has three advantages over the current state-of-the-art method in that it is fast, utilizes more inlier sensor data that does not become contaminated by severe sensor noise and extracts more accurate plane parameters.

Original languageEnglish
Article number17107508
Pages (from-to)203-212
Number of pages10
JournalIndustrial Robot
Volume41
Issue number2
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Sensors
Principal component analysis

Keywords

  • Hierarchical segmentation
  • Plane extraction
  • Plane registration
  • Robust PCA

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Robust-PCA-based hierarchical plane extraction for application to geometric 3D indoor mapping. / Yeon, Suyong; Jun, Changhyun; Choi, Hyunga; Kang, Jaehyeon; Yun, Youngmok; Doh, Nakju.

In: Industrial Robot, Vol. 41, No. 2, 17107508, 01.01.2014, p. 203-212.

Research output: Contribution to journalArticle

Yeon, Suyong ; Jun, Changhyun ; Choi, Hyunga ; Kang, Jaehyeon ; Yun, Youngmok ; Doh, Nakju. / Robust-PCA-based hierarchical plane extraction for application to geometric 3D indoor mapping. In: Industrial Robot. 2014 ; Vol. 41, No. 2. pp. 203-212.
@article{0a9a30660f6046d094cb02f445552379,
title = "Robust-PCA-based hierarchical plane extraction for application to geometric 3D indoor mapping",
abstract = "Purpose - The authors aim to propose a novel plane extraction algorithm for geometric 3D indoor mapping with range scan data. Design/methodology/approach - The proposed method utilizes a divide-and-conquer step to efficiently handle huge amounts of point clouds not in a whole group, but in forms of separate sub-groups with similar plane parameters. This method adopts robust principal component analysis to enhance estimation accuracy. Findings - Experimental results verify that the method not only shows enhanced performance in the plane extraction, but also broadens the domain of interest of the plane registration to an information-poor environment (such as simple indoor corridors), while the previous method only adequately works in an information-rich environment (such as a space with many features). Originality/value - The proposed algorithm has three advantages over the current state-of-the-art method in that it is fast, utilizes more inlier sensor data that does not become contaminated by severe sensor noise and extracts more accurate plane parameters.",
keywords = "Hierarchical segmentation, Plane extraction, Plane registration, Robust PCA",
author = "Suyong Yeon and Changhyun Jun and Hyunga Choi and Jaehyeon Kang and Youngmok Yun and Nakju Doh",
year = "2014",
month = "1",
day = "1",
doi = "10.1108/IR-04-2013-347",
language = "English",
volume = "41",
pages = "203--212",
journal = "Industrial Robot",
issn = "0143-991X",
publisher = "Emerald Group Publishing Ltd.",
number = "2",

}

TY - JOUR

T1 - Robust-PCA-based hierarchical plane extraction for application to geometric 3D indoor mapping

AU - Yeon, Suyong

AU - Jun, Changhyun

AU - Choi, Hyunga

AU - Kang, Jaehyeon

AU - Yun, Youngmok

AU - Doh, Nakju

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Purpose - The authors aim to propose a novel plane extraction algorithm for geometric 3D indoor mapping with range scan data. Design/methodology/approach - The proposed method utilizes a divide-and-conquer step to efficiently handle huge amounts of point clouds not in a whole group, but in forms of separate sub-groups with similar plane parameters. This method adopts robust principal component analysis to enhance estimation accuracy. Findings - Experimental results verify that the method not only shows enhanced performance in the plane extraction, but also broadens the domain of interest of the plane registration to an information-poor environment (such as simple indoor corridors), while the previous method only adequately works in an information-rich environment (such as a space with many features). Originality/value - The proposed algorithm has three advantages over the current state-of-the-art method in that it is fast, utilizes more inlier sensor data that does not become contaminated by severe sensor noise and extracts more accurate plane parameters.

AB - Purpose - The authors aim to propose a novel plane extraction algorithm for geometric 3D indoor mapping with range scan data. Design/methodology/approach - The proposed method utilizes a divide-and-conquer step to efficiently handle huge amounts of point clouds not in a whole group, but in forms of separate sub-groups with similar plane parameters. This method adopts robust principal component analysis to enhance estimation accuracy. Findings - Experimental results verify that the method not only shows enhanced performance in the plane extraction, but also broadens the domain of interest of the plane registration to an information-poor environment (such as simple indoor corridors), while the previous method only adequately works in an information-rich environment (such as a space with many features). Originality/value - The proposed algorithm has three advantages over the current state-of-the-art method in that it is fast, utilizes more inlier sensor data that does not become contaminated by severe sensor noise and extracts more accurate plane parameters.

KW - Hierarchical segmentation

KW - Plane extraction

KW - Plane registration

KW - Robust PCA

UR - http://www.scopus.com/inward/record.url?scp=84897401505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897401505&partnerID=8YFLogxK

U2 - 10.1108/IR-04-2013-347

DO - 10.1108/IR-04-2013-347

M3 - Article

AN - SCOPUS:84897401505

VL - 41

SP - 203

EP - 212

JO - Industrial Robot

JF - Industrial Robot

SN - 0143-991X

IS - 2

M1 - 17107508

ER -