Robust range image registration using local distribution of albedo

Diego Thomas, Akihiro Sugimoto

研究成果: 著書/レポートタイプへの貢献会議での発言

抄録

We propose a robust registration method for range images under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, they are promising to range image registration of objects lacking in discriminative geometric features under variable illumination. In our method, we use adaptive regions to model the local distribution of reflectance, which enables us to stably extract reliable attributes of each point against illumination estimation. We use a level set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is defined using the principal component analysis to find matches. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.

元の言語英語
ホスト出版物のタイトル2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009
ページ1654-1661
ページ数8
DOI
出版物ステータス出版済み - 12 1 2009
外部発表Yes
イベント2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009 - Kyoto, 日本
継続期間: 9 27 200910 4 2009

出版物シリーズ

名前2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

その他

その他2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009
日本
Kyoto
期間9/27/0910/4/09

Fingerprint

Image registration
Lighting
Rigidity
Principal component analysis
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

これを引用

Thomas, D., & Sugimoto, A. (2009). Robust range image registration using local distribution of albedo. : 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009 (pp. 1654-1661). [5457482] (2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009). https://doi.org/10.1109/ICCVW.2009.5457482

Robust range image registration using local distribution of albedo. / Thomas, Diego; Sugimoto, Akihiro.

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009. 2009. p. 1654-1661 5457482 (2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009).

研究成果: 著書/レポートタイプへの貢献会議での発言

Thomas, D & Sugimoto, A 2009, Robust range image registration using local distribution of albedo. : 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009., 5457482, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, pp. 1654-1661, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009, Kyoto, 日本, 9/27/09. https://doi.org/10.1109/ICCVW.2009.5457482
Thomas D, Sugimoto A. Robust range image registration using local distribution of albedo. : 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009. 2009. p. 1654-1661. 5457482. (2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009). https://doi.org/10.1109/ICCVW.2009.5457482
Thomas, Diego ; Sugimoto, Akihiro. / Robust range image registration using local distribution of albedo. 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009. 2009. pp. 1654-1661 (2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009).
@inproceedings{deacf998e8c747b1975e59a6226b246f,
title = "Robust range image registration using local distribution of albedo",
abstract = "We propose a robust registration method for range images under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, they are promising to range image registration of objects lacking in discriminative geometric features under variable illumination. In our method, we use adaptive regions to model the local distribution of reflectance, which enables us to stably extract reliable attributes of each point against illumination estimation. We use a level set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is defined using the principal component analysis to find matches. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.",
author = "Diego Thomas and Akihiro Sugimoto",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ICCVW.2009.5457482",
language = "English",
isbn = "9781424444427",
series = "2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009",
pages = "1654--1661",
booktitle = "2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009",

}

TY - GEN

T1 - Robust range image registration using local distribution of albedo

AU - Thomas, Diego

AU - Sugimoto, Akihiro

PY - 2009/12/1

Y1 - 2009/12/1

N2 - We propose a robust registration method for range images under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, they are promising to range image registration of objects lacking in discriminative geometric features under variable illumination. In our method, we use adaptive regions to model the local distribution of reflectance, which enables us to stably extract reliable attributes of each point against illumination estimation. We use a level set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is defined using the principal component analysis to find matches. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.

AB - We propose a robust registration method for range images under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, they are promising to range image registration of objects lacking in discriminative geometric features under variable illumination. In our method, we use adaptive regions to model the local distribution of reflectance, which enables us to stably extract reliable attributes of each point against illumination estimation. We use a level set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is defined using the principal component analysis to find matches. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=77953220309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953220309&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2009.5457482

DO - 10.1109/ICCVW.2009.5457482

M3 - Conference contribution

AN - SCOPUS:77953220309

SN - 9781424444427

T3 - 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

SP - 1654

EP - 1661

BT - 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops 2009

ER -