Image feature-based SLAM for flat surface modeling in indoor environment

Tamaki Kobayashi, Masafumi Nakagawa

Research output: Contribution to conferencePaper

Abstract

In this study, we focused on image features in point cloud data to improve robustness of simultaneous localization and mapping (SLAM) for indoor mapping. We also focused on 3D area scanner to acquire point cloud data with reflection intensity images for image feature-based SLAM. Our methodology consists of five steps. First, point cloud data are acquired using a time-of-flight (TOF) camera from continuous viewpoints. Second, intensity images are generated from point cloud data. Third, the feature points are estimated from reflection intensity images with feature descriptors. Fourth, camera rotation matrices are estimated using corresponded feature points in intensity images. Finally, acquired point cloud data are registered using the estimated rotation matrices. We clarified that our methodology can integrate point cloud data successfully through our experiments in indoor environments.

Original languageEnglish
Publication statusPublished - 2017 Jan 1
Event38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017 - New Delhi, India
Duration: 2017 Oct 232017 Oct 27

Other

Other38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017
CountryIndia
CityNew Delhi
Period17/10/2317/10/27

Fingerprint

Cameras
Experiments

Keywords

  • Indoor mapping
  • Iterative closest point
  • Mapping
  • Point clouds
  • Simultaneous localization
  • Time-of-flight camera

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Kobayashi, T., & Nakagawa, M. (2017). Image feature-based SLAM for flat surface modeling in indoor environment. Paper presented at 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017, New Delhi, India.

Image feature-based SLAM for flat surface modeling in indoor environment. / Kobayashi, Tamaki; Nakagawa, Masafumi.

2017. Paper presented at 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017, New Delhi, India.

Research output: Contribution to conferencePaper

Kobayashi, T & Nakagawa, M 2017, 'Image feature-based SLAM for flat surface modeling in indoor environment' Paper presented at 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017, New Delhi, India, 17/10/23 - 17/10/27, .
Kobayashi T, Nakagawa M. Image feature-based SLAM for flat surface modeling in indoor environment. 2017. Paper presented at 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017, New Delhi, India.
Kobayashi, Tamaki ; Nakagawa, Masafumi. / Image feature-based SLAM for flat surface modeling in indoor environment. Paper presented at 38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017, New Delhi, India.
@conference{92f87a10043b462aadc23f81990189da,
title = "Image feature-based SLAM for flat surface modeling in indoor environment",
abstract = "In this study, we focused on image features in point cloud data to improve robustness of simultaneous localization and mapping (SLAM) for indoor mapping. We also focused on 3D area scanner to acquire point cloud data with reflection intensity images for image feature-based SLAM. Our methodology consists of five steps. First, point cloud data are acquired using a time-of-flight (TOF) camera from continuous viewpoints. Second, intensity images are generated from point cloud data. Third, the feature points are estimated from reflection intensity images with feature descriptors. Fourth, camera rotation matrices are estimated using corresponded feature points in intensity images. Finally, acquired point cloud data are registered using the estimated rotation matrices. We clarified that our methodology can integrate point cloud data successfully through our experiments in indoor environments.",
keywords = "Indoor mapping, Iterative closest point, Mapping, Point clouds, Simultaneous localization, Time-of-flight camera",
author = "Tamaki Kobayashi and Masafumi Nakagawa",
year = "2017",
month = "1",
day = "1",
language = "English",
note = "38th Asian Conference on Remote Sensing - Space Applications: Touching Human Lives, ACRS 2017 ; Conference date: 23-10-2017 Through 27-10-2017",

}

TY - CONF

T1 - Image feature-based SLAM for flat surface modeling in indoor environment

AU - Kobayashi, Tamaki

AU - Nakagawa, Masafumi

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In this study, we focused on image features in point cloud data to improve robustness of simultaneous localization and mapping (SLAM) for indoor mapping. We also focused on 3D area scanner to acquire point cloud data with reflection intensity images for image feature-based SLAM. Our methodology consists of five steps. First, point cloud data are acquired using a time-of-flight (TOF) camera from continuous viewpoints. Second, intensity images are generated from point cloud data. Third, the feature points are estimated from reflection intensity images with feature descriptors. Fourth, camera rotation matrices are estimated using corresponded feature points in intensity images. Finally, acquired point cloud data are registered using the estimated rotation matrices. We clarified that our methodology can integrate point cloud data successfully through our experiments in indoor environments.

AB - In this study, we focused on image features in point cloud data to improve robustness of simultaneous localization and mapping (SLAM) for indoor mapping. We also focused on 3D area scanner to acquire point cloud data with reflection intensity images for image feature-based SLAM. Our methodology consists of five steps. First, point cloud data are acquired using a time-of-flight (TOF) camera from continuous viewpoints. Second, intensity images are generated from point cloud data. Third, the feature points are estimated from reflection intensity images with feature descriptors. Fourth, camera rotation matrices are estimated using corresponded feature points in intensity images. Finally, acquired point cloud data are registered using the estimated rotation matrices. We clarified that our methodology can integrate point cloud data successfully through our experiments in indoor environments.

KW - Indoor mapping

KW - Iterative closest point

KW - Mapping

KW - Point clouds

KW - Simultaneous localization

KW - Time-of-flight camera

UR - http://www.scopus.com/inward/record.url?scp=85047385874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047385874&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85047385874

ER -