Superpixel smoothing for disparity refinement in stereo matching

Chun Yi Sung, Yu Wen Tseng, Chin-Hsing Chen

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

Abstract

Stereo matching algorithms are mainly divided into two classes, local algorithm and global algorithm. Most local algorithms consist of four stages, initial cost computation, cost aggregation, disparity computation, and refinement. In this paper, we propose a method to enhance the disparity accuracy at regions near depth discontinuities. In the refinement stage, following the traditional Left-Right Consistency check, we classify each pixel by using superpixel segmentation. We then detect and correct outliers in superpixels. The experiments show that the disparity map generated by the proposed superpixel smoothing in the refinement stage is smoother than other existing methods.

Original languageEnglish
Title of host publicationProceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages50-53
Number of pages4
ISBN (Electronic)9781538670361
DOIs
Publication statusPublished - 2019 Feb 19
Event4th International Symposium on Computer, Consumer and Control, IS3C 2018 - Taichung, Taiwan
Duration: 2018 Dec 62018 Dec 8

Publication series

NameProceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018

Conference

Conference4th International Symposium on Computer, Consumer and Control, IS3C 2018
CountryTaiwan
CityTaichung
Period18-12-0618-12-08

Fingerprint

Stereo Matching
Smoothing
Local Algorithms
Refinement
Costs
Matching Algorithm
Outlier
Discontinuity
Aggregation
Segmentation
Pixel
Classify
Agglomeration
Pixels
Experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Control and Systems Engineering
  • Energy Engineering and Power Technology
  • Computer Science Applications
  • Control and Optimization
  • Signal Processing

Cite this

Sung, C. Y., Tseng, Y. W., & Chen, C-H. (2019). Superpixel smoothing for disparity refinement in stereo matching. In Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018 (pp. 50-53). [8644837] (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IS3C.2018.00021
Sung, Chun Yi ; Tseng, Yu Wen ; Chen, Chin-Hsing. / Superpixel smoothing for disparity refinement in stereo matching. Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 50-53 (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018).
@inproceedings{ecdbbd50a66248c38d8213a7b9b14dec,
title = "Superpixel smoothing for disparity refinement in stereo matching",
abstract = "Stereo matching algorithms are mainly divided into two classes, local algorithm and global algorithm. Most local algorithms consist of four stages, initial cost computation, cost aggregation, disparity computation, and refinement. In this paper, we propose a method to enhance the disparity accuracy at regions near depth discontinuities. In the refinement stage, following the traditional Left-Right Consistency check, we classify each pixel by using superpixel segmentation. We then detect and correct outliers in superpixels. The experiments show that the disparity map generated by the proposed superpixel smoothing in the refinement stage is smoother than other existing methods.",
author = "Sung, {Chun Yi} and Tseng, {Yu Wen} and Chin-Hsing Chen",
year = "2019",
month = "2",
day = "19",
doi = "10.1109/IS3C.2018.00021",
language = "English",
series = "Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "50--53",
booktitle = "Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018",
address = "United States",

}

Sung, CY, Tseng, YW & Chen, C-H 2019, Superpixel smoothing for disparity refinement in stereo matching. in Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018., 8644837, Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018, Institute of Electrical and Electronics Engineers Inc., pp. 50-53, 4th International Symposium on Computer, Consumer and Control, IS3C 2018, Taichung, Taiwan, 18-12-06. https://doi.org/10.1109/IS3C.2018.00021

Superpixel smoothing for disparity refinement in stereo matching. / Sung, Chun Yi; Tseng, Yu Wen; Chen, Chin-Hsing.

Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 50-53 8644837 (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018).

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

TY - GEN

T1 - Superpixel smoothing for disparity refinement in stereo matching

AU - Sung, Chun Yi

AU - Tseng, Yu Wen

AU - Chen, Chin-Hsing

PY - 2019/2/19

Y1 - 2019/2/19

N2 - Stereo matching algorithms are mainly divided into two classes, local algorithm and global algorithm. Most local algorithms consist of four stages, initial cost computation, cost aggregation, disparity computation, and refinement. In this paper, we propose a method to enhance the disparity accuracy at regions near depth discontinuities. In the refinement stage, following the traditional Left-Right Consistency check, we classify each pixel by using superpixel segmentation. We then detect and correct outliers in superpixels. The experiments show that the disparity map generated by the proposed superpixel smoothing in the refinement stage is smoother than other existing methods.

AB - Stereo matching algorithms are mainly divided into two classes, local algorithm and global algorithm. Most local algorithms consist of four stages, initial cost computation, cost aggregation, disparity computation, and refinement. In this paper, we propose a method to enhance the disparity accuracy at regions near depth discontinuities. In the refinement stage, following the traditional Left-Right Consistency check, we classify each pixel by using superpixel segmentation. We then detect and correct outliers in superpixels. The experiments show that the disparity map generated by the proposed superpixel smoothing in the refinement stage is smoother than other existing methods.

UR - http://www.scopus.com/inward/record.url?scp=85063238339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063238339&partnerID=8YFLogxK

U2 - 10.1109/IS3C.2018.00021

DO - 10.1109/IS3C.2018.00021

M3 - Conference contribution

AN - SCOPUS:85063238339

T3 - Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018

SP - 50

EP - 53

BT - Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Sung CY, Tseng YW, Chen C-H. Superpixel smoothing for disparity refinement in stereo matching. In Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 50-53. 8644837. (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018). https://doi.org/10.1109/IS3C.2018.00021