Live structural modeling using RGB-D SLAM

Nicolas Olivier, Hideaki Uchiyama, Masashi Mishima, Diego Gabriel Francis Thomas, Rin-Ichiro Taniguchi, Rafael Roberto, Joao Paulo Lima, Veronica Teichrieb

研究成果: 著書/レポートタイプへの貢献会議での発言

2 引用 (Scopus)

抄録

This paper presents a method for localizing primitive shapes in a dense point cloud computed by the RGB-D SLAM system. To stably generate a shape map containing only primitive shapes, the primitive shape is incrementally modeled by fusing the shapes estimated at previous frames in the SLAM, so that an accurate shape can be finally generated. Specifically, the history of the fusing process is used to avoid the influence of error accumulation in the SLAM. The point cloud of the shape is then updated by fusing the points in all the previous frames into a single point cloud. In the experimental results, we show that metric primitive modeling in texture-less and unprepared environments can be achieved online.

元の言語英語
ホスト出版物のタイトル2018 IEEE International Conference on Robotics and Automation, ICRA 2018
出版者Institute of Electrical and Electronics Engineers Inc.
ページ6352-6358
ページ数7
ISBN(電子版)9781538630815
DOI
出版物ステータス出版済み - 9 10 2018
イベント2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, オーストラリア
継続期間: 5 21 20185 25 2018

出版物シリーズ

名前Proceedings - IEEE International Conference on Robotics and Automation
ISSN(印刷物)1050-4729

会議

会議2018 IEEE International Conference on Robotics and Automation, ICRA 2018
オーストラリア
Brisbane
期間5/21/185/25/18

Fingerprint

Textures

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

これを引用

Olivier, N., Uchiyama, H., Mishima, M., Thomas, D. G. F., Taniguchi, R-I., Roberto, R., ... Teichrieb, V. (2018). Live structural modeling using RGB-D SLAM. : 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 (pp. 6352-6358). [8460973] (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2018.8460973

Live structural modeling using RGB-D SLAM. / Olivier, Nicolas; Uchiyama, Hideaki; Mishima, Masashi; Thomas, Diego Gabriel Francis; Taniguchi, Rin-Ichiro; Roberto, Rafael; Lima, Joao Paulo; Teichrieb, Veronica.

2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 6352-6358 8460973 (Proceedings - IEEE International Conference on Robotics and Automation).

研究成果: 著書/レポートタイプへの貢献会議での発言

Olivier, N, Uchiyama, H, Mishima, M, Thomas, DGF, Taniguchi, R-I, Roberto, R, Lima, JP & Teichrieb, V 2018, Live structural modeling using RGB-D SLAM. : 2018 IEEE International Conference on Robotics and Automation, ICRA 2018., 8460973, Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 6352-6358, 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, オーストラリア, 5/21/18. https://doi.org/10.1109/ICRA.2018.8460973
Olivier N, Uchiyama H, Mishima M, Thomas DGF, Taniguchi R-I, Roberto R その他. Live structural modeling using RGB-D SLAM. : 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 6352-6358. 8460973. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2018.8460973
Olivier, Nicolas ; Uchiyama, Hideaki ; Mishima, Masashi ; Thomas, Diego Gabriel Francis ; Taniguchi, Rin-Ichiro ; Roberto, Rafael ; Lima, Joao Paulo ; Teichrieb, Veronica. / Live structural modeling using RGB-D SLAM. 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 6352-6358 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{11cbf4729ca14f35b0250a8db476d11c,
title = "Live structural modeling using RGB-D SLAM",
abstract = "This paper presents a method for localizing primitive shapes in a dense point cloud computed by the RGB-D SLAM system. To stably generate a shape map containing only primitive shapes, the primitive shape is incrementally modeled by fusing the shapes estimated at previous frames in the SLAM, so that an accurate shape can be finally generated. Specifically, the history of the fusing process is used to avoid the influence of error accumulation in the SLAM. The point cloud of the shape is then updated by fusing the points in all the previous frames into a single point cloud. In the experimental results, we show that metric primitive modeling in texture-less and unprepared environments can be achieved online.",
author = "Nicolas Olivier and Hideaki Uchiyama and Masashi Mishima and Thomas, {Diego Gabriel Francis} and Rin-Ichiro Taniguchi and Rafael Roberto and Lima, {Joao Paulo} and Veronica Teichrieb",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/ICRA.2018.8460973",
language = "English",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "6352--6358",
booktitle = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018",
address = "United States",

}

TY - GEN

T1 - Live structural modeling using RGB-D SLAM

AU - Olivier, Nicolas

AU - Uchiyama, Hideaki

AU - Mishima, Masashi

AU - Thomas, Diego Gabriel Francis

AU - Taniguchi, Rin-Ichiro

AU - Roberto, Rafael

AU - Lima, Joao Paulo

AU - Teichrieb, Veronica

PY - 2018/9/10

Y1 - 2018/9/10

N2 - This paper presents a method for localizing primitive shapes in a dense point cloud computed by the RGB-D SLAM system. To stably generate a shape map containing only primitive shapes, the primitive shape is incrementally modeled by fusing the shapes estimated at previous frames in the SLAM, so that an accurate shape can be finally generated. Specifically, the history of the fusing process is used to avoid the influence of error accumulation in the SLAM. The point cloud of the shape is then updated by fusing the points in all the previous frames into a single point cloud. In the experimental results, we show that metric primitive modeling in texture-less and unprepared environments can be achieved online.

AB - This paper presents a method for localizing primitive shapes in a dense point cloud computed by the RGB-D SLAM system. To stably generate a shape map containing only primitive shapes, the primitive shape is incrementally modeled by fusing the shapes estimated at previous frames in the SLAM, so that an accurate shape can be finally generated. Specifically, the history of the fusing process is used to avoid the influence of error accumulation in the SLAM. The point cloud of the shape is then updated by fusing the points in all the previous frames into a single point cloud. In the experimental results, we show that metric primitive modeling in texture-less and unprepared environments can be achieved online.

UR - http://www.scopus.com/inward/record.url?scp=85061697007&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061697007&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2018.8460973

DO - 10.1109/ICRA.2018.8460973

M3 - Conference contribution

AN - SCOPUS:85061697007

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 6352

EP - 6358

BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -