Disparity refinement with stability-based tree for stereo matching

Yuhang Ji, Qieshi Zhang, Kenjiro Sugimoto, Seiichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 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 languageEnglish
Title of host publicationIEEE Intelligent Vehicles Symposium, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages469-474
Number of pages6
Volume2015-August
ISBN (Print)9781467372664
DOIs
Publication statusPublished - 2015 Aug 26
EventIEEE Intelligent Vehicles Symposium, IV 2015 - Seoul, Korea, Republic of
Duration: 2015 Jun 282015 Jul 1

Other

OtherIEEE Intelligent Vehicles Symposium, IV 2015
CountryKorea, Republic of
CitySeoul
Period15/6/2815/7/1

ASJC Scopus subject areas

  • Computer Science Applications
  • Automotive Engineering
  • Modelling and Simulation

Fingerprint Dive into the research topics of 'Disparity refinement with stability-based tree for stereo matching'. Together they form a unique fingerprint.

  • 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, pp. 469-474). [7225729] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IVS.2015.7225729