Two-stage cross-based stereo disparity refinement

Zonglin Xu, Seiichiro Kamata, Qieshi Zhang

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

Abstract

This paper proposed a disparity refinement method based on two-stage cross. First stage is anti-texture cross-based support region construction to build proper support regions for error pixels without being influenced by texture. Based on the support regions, second stage of the method is proposed, which is called weighted cross-based updating method. The experiments show that the proposed method could build the support region accurately and improve the accuracy of the disparity map in final results with fast speed, compared to other tree-based algorithms. It also outperforms the existing disparity refinement methods in preserving the boundaries of objects in the final disparity map.

Original languageEnglish
Title of host publicationProceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages420-423
Number of pages4
ISBN (Electronic)9784901122160
DOIs
Publication statusPublished - 2017 Jul 19
Event15th IAPR International Conference on Machine Vision Applications, MVA 2017 - Nagoya, Japan
Duration: 2017 May 82017 May 12

Other

Other15th IAPR International Conference on Machine Vision Applications, MVA 2017
CountryJapan
CityNagoya
Period17/5/817/5/12

Fingerprint

Textures
Pixels
Experiments

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Xu, Z., Kamata, S., & Zhang, Q. (2017). Two-stage cross-based stereo disparity refinement. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017 (pp. 420-423). [7986890] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2017.7986890

Two-stage cross-based stereo disparity refinement. / Xu, Zonglin; Kamata, Seiichiro; Zhang, Qieshi.

Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 420-423 7986890.

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

Xu, Z, Kamata, S & Zhang, Q 2017, Two-stage cross-based stereo disparity refinement. in Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017., 7986890, Institute of Electrical and Electronics Engineers Inc., pp. 420-423, 15th IAPR International Conference on Machine Vision Applications, MVA 2017, Nagoya, Japan, 17/5/8. https://doi.org/10.23919/MVA.2017.7986890
Xu Z, Kamata S, Zhang Q. Two-stage cross-based stereo disparity refinement. In Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 420-423. 7986890 https://doi.org/10.23919/MVA.2017.7986890
Xu, Zonglin ; Kamata, Seiichiro ; Zhang, Qieshi. / Two-stage cross-based stereo disparity refinement. Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 420-423
@inproceedings{44677b0108a642248493eb59e541242f,
title = "Two-stage cross-based stereo disparity refinement",
abstract = "This paper proposed a disparity refinement method based on two-stage cross. First stage is anti-texture cross-based support region construction to build proper support regions for error pixels without being influenced by texture. Based on the support regions, second stage of the method is proposed, which is called weighted cross-based updating method. The experiments show that the proposed method could build the support region accurately and improve the accuracy of the disparity map in final results with fast speed, compared to other tree-based algorithms. It also outperforms the existing disparity refinement methods in preserving the boundaries of objects in the final disparity map.",
author = "Zonglin Xu and Seiichiro Kamata and Qieshi Zhang",
year = "2017",
month = "7",
day = "19",
doi = "10.23919/MVA.2017.7986890",
language = "English",
pages = "420--423",
booktitle = "Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Two-stage cross-based stereo disparity refinement

AU - Xu, Zonglin

AU - Kamata, Seiichiro

AU - Zhang, Qieshi

PY - 2017/7/19

Y1 - 2017/7/19

N2 - This paper proposed a disparity refinement method based on two-stage cross. First stage is anti-texture cross-based support region construction to build proper support regions for error pixels without being influenced by texture. Based on the support regions, second stage of the method is proposed, which is called weighted cross-based updating method. The experiments show that the proposed method could build the support region accurately and improve the accuracy of the disparity map in final results with fast speed, compared to other tree-based algorithms. It also outperforms the existing disparity refinement methods in preserving the boundaries of objects in the final disparity map.

AB - This paper proposed a disparity refinement method based on two-stage cross. First stage is anti-texture cross-based support region construction to build proper support regions for error pixels without being influenced by texture. Based on the support regions, second stage of the method is proposed, which is called weighted cross-based updating method. The experiments show that the proposed method could build the support region accurately and improve the accuracy of the disparity map in final results with fast speed, compared to other tree-based algorithms. It also outperforms the existing disparity refinement methods in preserving the boundaries of objects in the final disparity map.

UR - http://www.scopus.com/inward/record.url?scp=85027865946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027865946&partnerID=8YFLogxK

U2 - 10.23919/MVA.2017.7986890

DO - 10.23919/MVA.2017.7986890

M3 - Conference contribution

AN - SCOPUS:85027865946

SP - 420

EP - 423

BT - Proceedings of the 15th IAPR International Conference on Machine Vision Applications, MVA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -