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

Graduate School of Information, Production and Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

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.

Original language	English
Title of host publication	IEEE Intelligent Vehicles Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	469-474
Number of pages	6
Volume	2015-August
ISBN (Print)	9781467372664
DOIs	https://doi.org/10.1109/IVS.2015.7225729
Publication status	Published - 2015 Aug 26
Event	IEEE Intelligent Vehicles Symposium, IV 2015 - Seoul, Korea, Republic of Duration: 2015 Jun 28 → 2015 Jul 1

Other

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

ASJC Scopus subject areas

Computer Science Applications
Automotive Engineering
Modelling and Simulation

Access to Document

10.1109/IVS.2015.7225729

Cite this

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 -

Disparity refinement with stability-based tree for stereo matching

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this