Transparent Random Dot Markers

Hideaki Uchiyama, Yuji Oyamada

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

This paper presents random dot markers (RDM) printed on transparent sheets as transparent fiducial markers. They are extremely unobstructive, and useful for developing novel user interfaces. However, the marker identification is required to be robust to observable back sides of the transparent sheets. To realize such markers, we propose a graph based framework for geometric feature based robust point matching for RDM. Instead of building one-to-one correspondences, we first build one-to-many correspondences using a 2D affinity matrix, and then globally optimize the matching assignment from the matrix. Especially, we incorporate pairwise relationship between neighboring points using local geometric descriptors into the matrix, and finally solve it with spectral matching. In the evaluation, we investigate the effectiveness of the global assignment from one-to-many correspondences, and finally show that our proposed method is enough robust to identifying overlapped markers.

元の言語英語
ホスト出版物のタイトル2018 24th International Conference on Pattern Recognition, ICPR 2018
出版者Institute of Electrical and Electronics Engineers Inc.
ページ254-259
ページ数6
ISBN(電子版)9781538637883
DOI
出版物ステータス出版済み - 11 26 2018
イベント24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, 中国
継続期間: 8 20 20188 24 2018

出版物シリーズ

名前Proceedings - International Conference on Pattern Recognition
2018-August
ISSN(印刷物)1051-4651

その他

その他24th International Conference on Pattern Recognition, ICPR 2018
中国
Beijing
期間8/20/188/24/18

Fingerprint

User interfaces

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

これを引用

Uchiyama, H., & Oyamada, Y. (2018). Transparent Random Dot Markers. : 2018 24th International Conference on Pattern Recognition, ICPR 2018 (pp. 254-259). [8545845] (Proceedings - International Conference on Pattern Recognition; 巻数 2018-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8545845

Transparent Random Dot Markers. / Uchiyama, Hideaki; Oyamada, Yuji.

2018 24th International Conference on Pattern Recognition, ICPR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 254-259 8545845 (Proceedings - International Conference on Pattern Recognition; 巻 2018-August).

研究成果: 著書/レポートタイプへの貢献会議での発言

Uchiyama, H & Oyamada, Y 2018, Transparent Random Dot Markers. : 2018 24th International Conference on Pattern Recognition, ICPR 2018., 8545845, Proceedings - International Conference on Pattern Recognition, 巻. 2018-August, Institute of Electrical and Electronics Engineers Inc., pp. 254-259, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, 中国, 8/20/18. https://doi.org/10.1109/ICPR.2018.8545845
Uchiyama H, Oyamada Y. Transparent Random Dot Markers. : 2018 24th International Conference on Pattern Recognition, ICPR 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 254-259. 8545845. (Proceedings - International Conference on Pattern Recognition). https://doi.org/10.1109/ICPR.2018.8545845
Uchiyama, Hideaki ; Oyamada, Yuji. / Transparent Random Dot Markers. 2018 24th International Conference on Pattern Recognition, ICPR 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 254-259 (Proceedings - International Conference on Pattern Recognition).
@inproceedings{5821fbf4471c4091a932460f41a19625,
title = "Transparent Random Dot Markers",
abstract = "This paper presents random dot markers (RDM) printed on transparent sheets as transparent fiducial markers. They are extremely unobstructive, and useful for developing novel user interfaces. However, the marker identification is required to be robust to observable back sides of the transparent sheets. To realize such markers, we propose a graph based framework for geometric feature based robust point matching for RDM. Instead of building one-to-one correspondences, we first build one-to-many correspondences using a 2D affinity matrix, and then globally optimize the matching assignment from the matrix. Especially, we incorporate pairwise relationship between neighboring points using local geometric descriptors into the matrix, and finally solve it with spectral matching. In the evaluation, we investigate the effectiveness of the global assignment from one-to-many correspondences, and finally show that our proposed method is enough robust to identifying overlapped markers.",
author = "Hideaki Uchiyama and Yuji Oyamada",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/ICPR.2018.8545845",
language = "English",
series = "Proceedings - International Conference on Pattern Recognition",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "254--259",
booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",
address = "United States",

}

TY - GEN

T1 - Transparent Random Dot Markers

AU - Uchiyama, Hideaki

AU - Oyamada, Yuji

PY - 2018/11/26

Y1 - 2018/11/26

N2 - This paper presents random dot markers (RDM) printed on transparent sheets as transparent fiducial markers. They are extremely unobstructive, and useful for developing novel user interfaces. However, the marker identification is required to be robust to observable back sides of the transparent sheets. To realize such markers, we propose a graph based framework for geometric feature based robust point matching for RDM. Instead of building one-to-one correspondences, we first build one-to-many correspondences using a 2D affinity matrix, and then globally optimize the matching assignment from the matrix. Especially, we incorporate pairwise relationship between neighboring points using local geometric descriptors into the matrix, and finally solve it with spectral matching. In the evaluation, we investigate the effectiveness of the global assignment from one-to-many correspondences, and finally show that our proposed method is enough robust to identifying overlapped markers.

AB - This paper presents random dot markers (RDM) printed on transparent sheets as transparent fiducial markers. They are extremely unobstructive, and useful for developing novel user interfaces. However, the marker identification is required to be robust to observable back sides of the transparent sheets. To realize such markers, we propose a graph based framework for geometric feature based robust point matching for RDM. Instead of building one-to-one correspondences, we first build one-to-many correspondences using a 2D affinity matrix, and then globally optimize the matching assignment from the matrix. Especially, we incorporate pairwise relationship between neighboring points using local geometric descriptors into the matrix, and finally solve it with spectral matching. In the evaluation, we investigate the effectiveness of the global assignment from one-to-many correspondences, and finally show that our proposed method is enough robust to identifying overlapped markers.

UR - http://www.scopus.com/inward/record.url?scp=85059777635&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059777635&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2018.8545845

DO - 10.1109/ICPR.2018.8545845

M3 - Conference contribution

AN - SCOPUS:85059777635

T3 - Proceedings - International Conference on Pattern Recognition

SP - 254

EP - 259

BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -