Incremental Structural Modeling Based on Geometric and Statistical Analyses

Rafael Roberto, João Paulo Lima, Hideaki Uchiyama, Clemens Arth, Veronica Teichrieb, Rin-Ichiro Taniguchi, DIeter Schmalstieg

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

Finding high-level semantic information from a point cloud is a challenging task, and it can be used in various applications. For instance, it is useful to compactly represent the scene structure and efficiently understand the scene context. This task is even more challenging when using a hand-held monocular visual SLAM system that outputs a noisy sparse point cloud. In order to tackle this issue, we propose an incremental primitive modeling method using both geometric and statistical analyses for such point cloud. The main idea is to select only reliably-modeled shapes by analyzing the geometric relationship between the point cloud and the estimated shapes. Besides that, a statistical evaluation is incorporated to filter wrongly-detected primitives in a noisy point cloud. As a result of this processing, our approach largely improved precision when compared with state of the art methods. We also show the impact of segmenting and representing a scene using primitives instead of a point cloud.

元の言語英語
ホスト出版物のタイトルProceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018
出版者Institute of Electrical and Electronics Engineers Inc.
ページ955-963
ページ数9
2018-January
ISBN(電子版)9781538648865
DOI
出版物ステータス出版済み - 5 3 2018
イベント18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018 - Lake Tahoe, 米国
継続期間: 3 12 20183 15 2018

その他

その他18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018
米国
Lake Tahoe
期間3/12/183/15/18

Fingerprint

Semantics
Processing

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

これを引用

Roberto, R., Lima, J. P., Uchiyama, H., Arth, C., Teichrieb, V., Taniguchi, R-I., & Schmalstieg, DI. (2018). Incremental Structural Modeling Based on Geometric and Statistical Analyses. : Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018 (巻 2018-January, pp. 955-963). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WACV.2018.00110

Incremental Structural Modeling Based on Geometric and Statistical Analyses. / Roberto, Rafael; Lima, João Paulo; Uchiyama, Hideaki; Arth, Clemens; Teichrieb, Veronica; Taniguchi, Rin-Ichiro; Schmalstieg, DIeter.

Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018. 巻 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 955-963.

研究成果: 著書/レポートタイプへの貢献会議での発言

Roberto, R, Lima, JP, Uchiyama, H, Arth, C, Teichrieb, V, Taniguchi, R-I & Schmalstieg, DI 2018, Incremental Structural Modeling Based on Geometric and Statistical Analyses. : Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018. 巻. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 955-963, 18th IEEE Winter Conference on Applications of Computer Vision, WACV 2018, Lake Tahoe, 米国, 3/12/18. https://doi.org/10.1109/WACV.2018.00110
Roberto R, Lima JP, Uchiyama H, Arth C, Teichrieb V, Taniguchi R-I その他. Incremental Structural Modeling Based on Geometric and Statistical Analyses. : Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018. 巻 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 955-963 https://doi.org/10.1109/WACV.2018.00110
Roberto, Rafael ; Lima, João Paulo ; Uchiyama, Hideaki ; Arth, Clemens ; Teichrieb, Veronica ; Taniguchi, Rin-Ichiro ; Schmalstieg, DIeter. / Incremental Structural Modeling Based on Geometric and Statistical Analyses. Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018. 巻 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 955-963
@inproceedings{1b418e0466e94ce1aaa4c4c6b2f54081,
title = "Incremental Structural Modeling Based on Geometric and Statistical Analyses",
abstract = "Finding high-level semantic information from a point cloud is a challenging task, and it can be used in various applications. For instance, it is useful to compactly represent the scene structure and efficiently understand the scene context. This task is even more challenging when using a hand-held monocular visual SLAM system that outputs a noisy sparse point cloud. In order to tackle this issue, we propose an incremental primitive modeling method using both geometric and statistical analyses for such point cloud. The main idea is to select only reliably-modeled shapes by analyzing the geometric relationship between the point cloud and the estimated shapes. Besides that, a statistical evaluation is incorporated to filter wrongly-detected primitives in a noisy point cloud. As a result of this processing, our approach largely improved precision when compared with state of the art methods. We also show the impact of segmenting and representing a scene using primitives instead of a point cloud.",
author = "Rafael Roberto and Lima, {Jo{\~a}o Paulo} and Hideaki Uchiyama and Clemens Arth and Veronica Teichrieb and Rin-Ichiro Taniguchi and DIeter Schmalstieg",
year = "2018",
month = "5",
day = "3",
doi = "10.1109/WACV.2018.00110",
language = "English",
volume = "2018-January",
pages = "955--963",
booktitle = "Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Incremental Structural Modeling Based on Geometric and Statistical Analyses

AU - Roberto, Rafael

AU - Lima, João Paulo

AU - Uchiyama, Hideaki

AU - Arth, Clemens

AU - Teichrieb, Veronica

AU - Taniguchi, Rin-Ichiro

AU - Schmalstieg, DIeter

PY - 2018/5/3

Y1 - 2018/5/3

N2 - Finding high-level semantic information from a point cloud is a challenging task, and it can be used in various applications. For instance, it is useful to compactly represent the scene structure and efficiently understand the scene context. This task is even more challenging when using a hand-held monocular visual SLAM system that outputs a noisy sparse point cloud. In order to tackle this issue, we propose an incremental primitive modeling method using both geometric and statistical analyses for such point cloud. The main idea is to select only reliably-modeled shapes by analyzing the geometric relationship between the point cloud and the estimated shapes. Besides that, a statistical evaluation is incorporated to filter wrongly-detected primitives in a noisy point cloud. As a result of this processing, our approach largely improved precision when compared with state of the art methods. We also show the impact of segmenting and representing a scene using primitives instead of a point cloud.

AB - Finding high-level semantic information from a point cloud is a challenging task, and it can be used in various applications. For instance, it is useful to compactly represent the scene structure and efficiently understand the scene context. This task is even more challenging when using a hand-held monocular visual SLAM system that outputs a noisy sparse point cloud. In order to tackle this issue, we propose an incremental primitive modeling method using both geometric and statistical analyses for such point cloud. The main idea is to select only reliably-modeled shapes by analyzing the geometric relationship between the point cloud and the estimated shapes. Besides that, a statistical evaluation is incorporated to filter wrongly-detected primitives in a noisy point cloud. As a result of this processing, our approach largely improved precision when compared with state of the art methods. We also show the impact of segmenting and representing a scene using primitives instead of a point cloud.

UR - http://www.scopus.com/inward/record.url?scp=85050993882&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050993882&partnerID=8YFLogxK

U2 - 10.1109/WACV.2018.00110

DO - 10.1109/WACV.2018.00110

M3 - Conference contribution

AN - SCOPUS:85050993882

VL - 2018-January

SP - 955

EP - 963

BT - Proceedings - 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -