Disparity refinement with stability-based tree for stereo matching

Yuhang Ji; Qieshi Zhang; Kenjiro Sugimoto; Seiichiro Kamata

doi:10.1109/IVS.2015.7225729

Disparity refinement with stability-based tree for stereo matching

Yuhang Ji, Qieshi Zhang, Kenjiro Sugimoto, Seiichiro Kamata

大学院情報生産システム研究科

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

This paper proposes a disparity refinement method with stability-based tree. By developing stability-based tree to evaluate and reconstruct support regions for error parts, the proposed method achieves effective performance in removing outliers. This approach further improves the quality of raw disparity map in stereo matching, which makes the local methods results comparable to the global ones. Experiments exhibit that the proposed method reduces more than 70% aggregation time compared with traditional tree method without loss of accuracy. It also outperforms existing disparity refinement methods in removing large error parts.

本文言語	English
ホスト出版物のタイトル	IEEE Intelligent Vehicles Symposium, Proceedings
出版社	Institute of Electrical and Electronics Engineers Inc.
ページ	469-474
ページ数	6
巻	2015-August
ISBN（印刷版）	9781467372664
DOI	https://doi.org/10.1109/IVS.2015.7225729
出版ステータス	Published - 2015 8 26
イベント	IEEE Intelligent Vehicles Symposium, IV 2015 - Seoul, Korea, Republic of 継続期間: 2015 6 28 → 2015 7 1

Other

Other	IEEE Intelligent Vehicles Symposium, IV 2015
Country	Korea, Republic of
City	Seoul
Period	15/6/28 → 15/7/1

ASJC Scopus subject areas

Computer Science Applications
Automotive Engineering
Modelling and Simulation

文献へのアクセス

10.1109/IVS.2015.7225729

フィンガープリント「Disparity refinement with stability-based tree for stereo matching」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル

Ji, Y, Zhang, Q, Sugimoto, K & Kamata, S 2015, Disparity refinement with stability-based tree for stereo matching. in IEEE Intelligent Vehicles Symposium, Proceedings. vol. 2015-August, 7225729, Institute of Electrical and Electronics Engineers Inc., pp. 469-474, IEEE Intelligent Vehicles Symposium, IV 2015, Seoul, Korea, Republic of, 15/6/28. https://doi.org/10.1109/IVS.2015.7225729

@inproceedings{7eb1b881eef24beab62c674a0259b32f,

title = "Disparity refinement with stability-based tree for stereo matching",

abstract = "This paper proposes a disparity refinement method with stability-based tree. By developing stability-based tree to evaluate and reconstruct support regions for error parts, the proposed method achieves effective performance in removing outliers. This approach further improves the quality of raw disparity map in stereo matching, which makes the local methods results comparable to the global ones. Experiments exhibit that the proposed method reduces more than 70% aggregation time compared with traditional tree method without loss of accuracy. It also outperforms existing disparity refinement methods in removing large error parts.",

author = "Yuhang Ji and Qieshi Zhang and Kenjiro Sugimoto and Seiichiro Kamata",

year = "2015",

month = aug,

day = "26",

doi = "10.1109/IVS.2015.7225729",

language = "English",

isbn = "9781467372664",

volume = "2015-August",

pages = "469--474",

booktitle = "IEEE Intelligent Vehicles Symposium, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "IEEE Intelligent Vehicles Symposium, IV 2015 ; Conference date: 28-06-2015 Through 01-07-2015",

}

TY - GEN

T1 - Disparity refinement with stability-based tree for stereo matching

AU - Ji, Yuhang

AU - Zhang, Qieshi

AU - Sugimoto, Kenjiro

AU - Kamata, Seiichiro

PY - 2015/8/26

Y1 - 2015/8/26

N2 - This paper proposes a disparity refinement method with stability-based tree. By developing stability-based tree to evaluate and reconstruct support regions for error parts, the proposed method achieves effective performance in removing outliers. This approach further improves the quality of raw disparity map in stereo matching, which makes the local methods results comparable to the global ones. Experiments exhibit that the proposed method reduces more than 70% aggregation time compared with traditional tree method without loss of accuracy. It also outperforms existing disparity refinement methods in removing large error parts.

AB - This paper proposes a disparity refinement method with stability-based tree. By developing stability-based tree to evaluate and reconstruct support regions for error parts, the proposed method achieves effective performance in removing outliers. This approach further improves the quality of raw disparity map in stereo matching, which makes the local methods results comparable to the global ones. Experiments exhibit that the proposed method reduces more than 70% aggregation time compared with traditional tree method without loss of accuracy. It also outperforms existing disparity refinement methods in removing large error parts.

UR - http://www.scopus.com/inward/record.url?scp=84951141511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951141511&partnerID=8YFLogxK

U2 - 10.1109/IVS.2015.7225729

DO - 10.1109/IVS.2015.7225729

M3 - Conference contribution

AN - SCOPUS:84951141511

SN - 9781467372664

VL - 2015-August

SP - 469

EP - 474

BT - IEEE Intelligent Vehicles Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE Intelligent Vehicles Symposium, IV 2015

Y2 - 28 June 2015 through 1 July 2015

ER -