Real-time 3D point cloud segmentation using Growing Neural Gas with Utility

Yuichiro Toda; Zhaojie Ju; Hui Yu; Naoyuki  Takesue; Kazuyoshi Wada; Naoyuki Kubota

doi:10.1109/HSI.2016.7529667

Real-time 3D point cloud segmentation using Growing Neural Gas with Utility

Yuichiro Toda, Zhaojie Ju, Hui Yu, Naoyuki Takesue, Kazuyoshi Wada , Naoyuki Kubota

Tokyo Metropolitan University

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

787 Downloads (Pure)

Abstract

This paper proposes a real-time feature extraction and segmentation method for a 3D point cloud. First of all, we apply Growing Neural Gas with Utility (GNG-U) to the point cloud for learning a topological structure. However, the standard GNG-U cannot learn the topological structure of 3D space environment and color information simultaneously. To this end, we then modify the GNG-U algorithm by using a weight vector. we propose a surface feature extraction and segmentation method by efficiently utilizing the topological structure. Our segmentation method is based on a region growing method whose similarity value uses the inner value of two normal vectors connected by the topological structure. We show experimental results of the proposed method and discuss the effectiveness of the proposed method.

Original language	English
Title of host publication	2016 9th International Conference on Human System Interactions (HSI)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	418-422
ISBN (Electronic)	978-1-5090-1729-4
ISBN (Print)	978-1-5090-1730-0
DOIs	https://doi.org/10.1109/HSI.2016.7529667
Publication status	Published - 4 Aug 2016
Event	9th International Conference on Human System Interactions: HSI 2016 - University of Portsmouth, Portsmouth, United Kingdom Duration: 6 Jul 2016 → 8 Jul 2016

Conference

Conference	9th International Conference on Human System Interactions
Abbreviated title	HSI 2016
Country/Territory	United Kingdom
City	Portsmouth
Period	6/07/16 → 8/07/16

Keywords

component
formatting
style
styling
insert (key words)

Access to Document

10.1109/HSI.2016.7529667

Real-time 3D point cloud segmentation using Growing Neural Gas with Utility
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 2.25 MB

Cite this

@inproceedings{c4759a0512f94ae09003859640d0e3f9,

title = "Real-time 3D point cloud segmentation using Growing Neural Gas with Utility",

abstract = "This paper proposes a real-time feature extraction and segmentation method for a 3D point cloud. First of all, we apply Growing Neural Gas with Utility (GNG-U) to the point cloud for learning a topological structure. However, the standard GNG-U cannot learn the topological structure of 3D space environment and color information simultaneously. To this end, we then modify the GNG-U algorithm by using a weight vector. we propose a surface feature extraction and segmentation method by efficiently utilizing the topological structure. Our segmentation method is based on a region growing method whose similarity value uses the inner value of two normal vectors connected by the topological structure. We show experimental results of the proposed method and discuss the effectiveness of the proposed method.",

keywords = "component, formatting, style, styling, insert (key words)",

author = "Yuichiro Toda and Zhaojie Ju and Hui Yu and Naoyuki Takesue and Kazuyoshi Wada and Naoyuki Kubota",

year = "2016",

month = aug,

day = "4",

doi = "10.1109/HSI.2016.7529667",

language = "English",

isbn = "978-1-5090-1730-0",

pages = "418--422",

booktitle = "2016 9th International Conference on Human System Interactions (HSI)",

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

address = "United States",

note = "9th International Conference on Human System Interactions : HSI 2016, HSI 2016 ; Conference date: 06-07-2016 Through 08-07-2016",

}

Toda, Y, Ju, Z, Yu, H, Takesue, N, Wada , K & Kubota, N 2016, Real-time 3D point cloud segmentation using Growing Neural Gas with Utility. in 2016 9th International Conference on Human System Interactions (HSI). Institute of Electrical and Electronics Engineers Inc., pp. 418-422, 9th International Conference on Human System Interactions, Portsmouth, United Kingdom, 6/07/16. https://doi.org/10.1109/HSI.2016.7529667

TY - GEN

T1 - Real-time 3D point cloud segmentation using Growing Neural Gas with Utility

AU - Toda, Yuichiro

AU - Ju, Zhaojie

AU - Yu, Hui

AU - Takesue, Naoyuki

AU - Wada , Kazuyoshi

AU - Kubota, Naoyuki

PY - 2016/8/4

Y1 - 2016/8/4

N2 - This paper proposes a real-time feature extraction and segmentation method for a 3D point cloud. First of all, we apply Growing Neural Gas with Utility (GNG-U) to the point cloud for learning a topological structure. However, the standard GNG-U cannot learn the topological structure of 3D space environment and color information simultaneously. To this end, we then modify the GNG-U algorithm by using a weight vector. we propose a surface feature extraction and segmentation method by efficiently utilizing the topological structure. Our segmentation method is based on a region growing method whose similarity value uses the inner value of two normal vectors connected by the topological structure. We show experimental results of the proposed method and discuss the effectiveness of the proposed method.

AB - This paper proposes a real-time feature extraction and segmentation method for a 3D point cloud. First of all, we apply Growing Neural Gas with Utility (GNG-U) to the point cloud for learning a topological structure. However, the standard GNG-U cannot learn the topological structure of 3D space environment and color information simultaneously. To this end, we then modify the GNG-U algorithm by using a weight vector. we propose a surface feature extraction and segmentation method by efficiently utilizing the topological structure. Our segmentation method is based on a region growing method whose similarity value uses the inner value of two normal vectors connected by the topological structure. We show experimental results of the proposed method and discuss the effectiveness of the proposed method.

KW - component

KW - formatting

KW - style

KW - styling

KW - insert (key words)

U2 - 10.1109/HSI.2016.7529667

DO - 10.1109/HSI.2016.7529667

M3 - Conference contribution

SN - 978-1-5090-1730-0

SP - 418

EP - 422

BT - 2016 9th International Conference on Human System Interactions (HSI)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Human System Interactions

Y2 - 6 July 2016 through 8 July 2016

ER -

Real-time 3D point cloud segmentation using Growing Neural Gas with Utility

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this