Categorization of indoor places by combining local binary pattern histograms of range and reflectance data from laser range finders

Oscar Martinez Mozos, Hitoshi Mizutani, Hojung Jung, Ryo Kurazume, Tsutomu Hasegawa

研究成果: ジャーナルへの寄稿記事

13 引用 (Scopus)

抄録

This paper presents an approach to categorize typical places in indoor environments using 3D scans provided by a laser range finder. Examples of such places are offices, laboratories, or kitchens. In our method, we combine the range and reflectance data from the laser scan for the final categorization of places. Range and reflectance images are transformed into histograms of local binary patterns and combined into a single feature vector. This vector is later classified using support vector machines. The results of the presented experiments demonstrate the capability of our technique to categorize indoor places with high accuracy. We also show that the combination of range and reflectance information improves the final categorization results in comparison with a single modality.

元の言語英語
ページ(範囲)1455-1464
ページ数10
ジャーナルAdvanced Robotics
27
発行部数18
DOI
出版物ステータス出版済み - 12 1 2013

Fingerprint

Range finders
Lasers
Kitchens
Support vector machines
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Human-Computer Interaction
  • Hardware and Architecture
  • Computer Science Applications

これを引用

Categorization of indoor places by combining local binary pattern histograms of range and reflectance data from laser range finders. / Mozos, Oscar Martinez; Mizutani, Hitoshi; Jung, Hojung; Kurazume, Ryo; Hasegawa, Tsutomu.

:: Advanced Robotics, 巻 27, 番号 18, 01.12.2013, p. 1455-1464.

研究成果: ジャーナルへの寄稿記事

Mozos, Oscar Martinez ; Mizutani, Hitoshi ; Jung, Hojung ; Kurazume, Ryo ; Hasegawa, Tsutomu. / Categorization of indoor places by combining local binary pattern histograms of range and reflectance data from laser range finders. :: Advanced Robotics. 2013 ; 巻 27, 番号 18. pp. 1455-1464.
@article{65944108532e4257a3d9a035821601ca,
title = "Categorization of indoor places by combining local binary pattern histograms of range and reflectance data from laser range finders",
abstract = "This paper presents an approach to categorize typical places in indoor environments using 3D scans provided by a laser range finder. Examples of such places are offices, laboratories, or kitchens. In our method, we combine the range and reflectance data from the laser scan for the final categorization of places. Range and reflectance images are transformed into histograms of local binary patterns and combined into a single feature vector. This vector is later classified using support vector machines. The results of the presented experiments demonstrate the capability of our technique to categorize indoor places with high accuracy. We also show that the combination of range and reflectance information improves the final categorization results in comparison with a single modality.",
author = "Mozos, {Oscar Martinez} and Hitoshi Mizutani and Hojung Jung and Ryo Kurazume and Tsutomu Hasegawa",
year = "2013",
month = "12",
day = "1",
doi = "10.1080/01691864.2013.839091",
language = "English",
volume = "27",
pages = "1455--1464",
journal = "Advanced Robotics",
issn = "0169-1864",
publisher = "Taylor and Francis Ltd.",
number = "18",

}

TY - JOUR

T1 - Categorization of indoor places by combining local binary pattern histograms of range and reflectance data from laser range finders

AU - Mozos, Oscar Martinez

AU - Mizutani, Hitoshi

AU - Jung, Hojung

AU - Kurazume, Ryo

AU - Hasegawa, Tsutomu

PY - 2013/12/1

Y1 - 2013/12/1

N2 - This paper presents an approach to categorize typical places in indoor environments using 3D scans provided by a laser range finder. Examples of such places are offices, laboratories, or kitchens. In our method, we combine the range and reflectance data from the laser scan for the final categorization of places. Range and reflectance images are transformed into histograms of local binary patterns and combined into a single feature vector. This vector is later classified using support vector machines. The results of the presented experiments demonstrate the capability of our technique to categorize indoor places with high accuracy. We also show that the combination of range and reflectance information improves the final categorization results in comparison with a single modality.

AB - This paper presents an approach to categorize typical places in indoor environments using 3D scans provided by a laser range finder. Examples of such places are offices, laboratories, or kitchens. In our method, we combine the range and reflectance data from the laser scan for the final categorization of places. Range and reflectance images are transformed into histograms of local binary patterns and combined into a single feature vector. This vector is later classified using support vector machines. The results of the presented experiments demonstrate the capability of our technique to categorize indoor places with high accuracy. We also show that the combination of range and reflectance information improves the final categorization results in comparison with a single modality.

UR - http://www.scopus.com/inward/record.url?scp=84886003910&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886003910&partnerID=8YFLogxK

U2 - 10.1080/01691864.2013.839091

DO - 10.1080/01691864.2013.839091

M3 - Article

AN - SCOPUS:84886003910

VL - 27

SP - 1455

EP - 1464

JO - Advanced Robotics

JF - Advanced Robotics

SN - 0169-1864

IS - 18

ER -