Towards a realistic indoor world reconstruction: preliminary results for an object-oriented 3D RGB-D mapping

Chang Hyun Jun, Jaehyeon Kang, Suyong Yeon, Hyunga Choi, Tae Young Chung, Nakju Doh

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

A real world reconstruction that generates cyberspace not from a computer graphics tool, but from the real world, has been one of the main issues in two different communities of robotics and computer vision under different names of Simultaneous Localization And Mapping (SLAM) and Structure from Motion (SfM). However, there have been few trials that actively integrate SLAM and SfM for possible synergy. This paper shows the real world reconstruction can be enabled through this integration. As a result, the preliminary map has been generated of which five subgoals are: Realistic view (RGB), accurate geometry (depth), applicability to multi-floor indoor building, initial classification of a possible set of objects, and full automation. To this end, an engineering framework of “Acquire-Build-Comprehend (ABC)” is proposed, through which a sensor system acquires an RGB-Depth point cloud from the real world, builds a three-dimensional map, and comprehends this map to yield the possible set of objects. Its performance is demonstrated by building a map for three levels of indoor building of which volume is 1,408 m3.

Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalIntelligent Automation and Soft Computing
DOIs
Publication statusAccepted/In press - 2016 Jun 7

Fingerprint

Object-oriented
Structure from Motion
Simultaneous Localization and Mapping
Point Cloud
Synergy
Computer graphics
Computer Vision
Computer vision
Automation
Robotics
Integrate
Engineering
Sensor
Three-dimensional
Geometry
Sensors
Object

Keywords

  • 3-dimensional map
  • Real world reconstruction
  • RGB-D
  • SfM
  • SLAM

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Towards a realistic indoor world reconstruction : preliminary results for an object-oriented 3D RGB-D mapping. / Jun, Chang Hyun; Kang, Jaehyeon; Yeon, Suyong; Choi, Hyunga; Chung, Tae Young; Doh, Nakju.

In: Intelligent Automation and Soft Computing, 07.06.2016, p. 1-12.

Research output: Contribution to journalArticle

Jun, Chang Hyun ; Kang, Jaehyeon ; Yeon, Suyong ; Choi, Hyunga ; Chung, Tae Young ; Doh, Nakju. / Towards a realistic indoor world reconstruction : preliminary results for an object-oriented 3D RGB-D mapping. In: Intelligent Automation and Soft Computing. 2016 ; pp. 1-12.
@article{8a9225c3985048f28edf7e28245f6625,
title = "Towards a realistic indoor world reconstruction: preliminary results for an object-oriented 3D RGB-D mapping",
abstract = "A real world reconstruction that generates cyberspace not from a computer graphics tool, but from the real world, has been one of the main issues in two different communities of robotics and computer vision under different names of Simultaneous Localization And Mapping (SLAM) and Structure from Motion (SfM). However, there have been few trials that actively integrate SLAM and SfM for possible synergy. This paper shows the real world reconstruction can be enabled through this integration. As a result, the preliminary map has been generated of which five subgoals are: Realistic view (RGB), accurate geometry (depth), applicability to multi-floor indoor building, initial classification of a possible set of objects, and full automation. To this end, an engineering framework of “Acquire-Build-Comprehend (ABC)” is proposed, through which a sensor system acquires an RGB-Depth point cloud from the real world, builds a three-dimensional map, and comprehends this map to yield the possible set of objects. Its performance is demonstrated by building a map for three levels of indoor building of which volume is 1,408 m3.",
keywords = "3-dimensional map, Real world reconstruction, RGB-D, SfM, SLAM",
author = "Jun, {Chang Hyun} and Jaehyeon Kang and Suyong Yeon and Hyunga Choi and Chung, {Tae Young} and Nakju Doh",
year = "2016",
month = "6",
day = "7",
doi = "10.1080/10798587.2016.1186890",
language = "English",
pages = "1--12",
journal = "Intelligent Automation and Soft Computing",
issn = "1079-8587",
publisher = "AutoSoft Press",

}

TY - JOUR

T1 - Towards a realistic indoor world reconstruction

T2 - preliminary results for an object-oriented 3D RGB-D mapping

AU - Jun, Chang Hyun

AU - Kang, Jaehyeon

AU - Yeon, Suyong

AU - Choi, Hyunga

AU - Chung, Tae Young

AU - Doh, Nakju

PY - 2016/6/7

Y1 - 2016/6/7

N2 - A real world reconstruction that generates cyberspace not from a computer graphics tool, but from the real world, has been one of the main issues in two different communities of robotics and computer vision under different names of Simultaneous Localization And Mapping (SLAM) and Structure from Motion (SfM). However, there have been few trials that actively integrate SLAM and SfM for possible synergy. This paper shows the real world reconstruction can be enabled through this integration. As a result, the preliminary map has been generated of which five subgoals are: Realistic view (RGB), accurate geometry (depth), applicability to multi-floor indoor building, initial classification of a possible set of objects, and full automation. To this end, an engineering framework of “Acquire-Build-Comprehend (ABC)” is proposed, through which a sensor system acquires an RGB-Depth point cloud from the real world, builds a three-dimensional map, and comprehends this map to yield the possible set of objects. Its performance is demonstrated by building a map for three levels of indoor building of which volume is 1,408 m3.

AB - A real world reconstruction that generates cyberspace not from a computer graphics tool, but from the real world, has been one of the main issues in two different communities of robotics and computer vision under different names of Simultaneous Localization And Mapping (SLAM) and Structure from Motion (SfM). However, there have been few trials that actively integrate SLAM and SfM for possible synergy. This paper shows the real world reconstruction can be enabled through this integration. As a result, the preliminary map has been generated of which five subgoals are: Realistic view (RGB), accurate geometry (depth), applicability to multi-floor indoor building, initial classification of a possible set of objects, and full automation. To this end, an engineering framework of “Acquire-Build-Comprehend (ABC)” is proposed, through which a sensor system acquires an RGB-Depth point cloud from the real world, builds a three-dimensional map, and comprehends this map to yield the possible set of objects. Its performance is demonstrated by building a map for three levels of indoor building of which volume is 1,408 m3.

KW - 3-dimensional map

KW - Real world reconstruction

KW - RGB-D

KW - SfM

KW - SLAM

UR - http://www.scopus.com/inward/record.url?scp=84976309715&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976309715&partnerID=8YFLogxK

U2 - 10.1080/10798587.2016.1186890

DO - 10.1080/10798587.2016.1186890

M3 - Article

AN - SCOPUS:84976309715

SP - 1

EP - 12

JO - Intelligent Automation and Soft Computing

JF - Intelligent Automation and Soft Computing

SN - 1079-8587

ER -