A revisit to cost aggregation in stereo matching

How far can we reduce its computational redundancy?

Dongbo Min, Jiangbo Lu, Minh N Do

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

Abstract

This paper presents a novel method for performing an efficient cost aggregation in stereo matching. The cost aggregation problem is re-formulated with a perspective of a histogram, and it gives us a potential to reduce the complexity of the cost aggregation significantly. Different from the previous methods which have tried to reduce the complexity in terms of the size of an image and a matching window, our approach focuses on reducing the computational redundancy which exists among the search range, caused by a repeated filtering for all disparity hypotheses. Moreover, we also reduce the complexity of the window-based filtering through an efficient sampling scheme inside the matching window. The trade-off between accuracy and complexity is extensively investigated into parameters used in the proposed method. Experimental results show that the proposed method provides high-quality disparity maps with low complexity. This work provides new insights into complexity-constrained stereo matching algorithm design.

Original languageEnglish (US)
Title of host publication2011 International Conference on Computer Vision, ICCV 2011
Pages1567-1574
Number of pages8
DOIs
StatePublished - Dec 1 2011
Event2011 IEEE International Conference on Computer Vision, ICCV 2011 - Barcelona, Spain
Duration: Nov 6 2011Nov 13 2011

Other

Other2011 IEEE International Conference on Computer Vision, ICCV 2011
CountrySpain
CityBarcelona
Period11/6/1111/13/11

Fingerprint

Redundancy
Agglomeration
Costs
Sampling

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Min, D., Lu, J., & Do, M. N. (2011). A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy? In 2011 International Conference on Computer Vision, ICCV 2011 (pp. 1567-1574). [6126416] https://doi.org/10.1109/ICCV.2011.6126416

A revisit to cost aggregation in stereo matching : How far can we reduce its computational redundancy? / Min, Dongbo; Lu, Jiangbo; Do, Minh N.

2011 International Conference on Computer Vision, ICCV 2011. 2011. p. 1567-1574 6126416.

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

Min, D, Lu, J & Do, MN 2011, A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy? in 2011 International Conference on Computer Vision, ICCV 2011., 6126416, pp. 1567-1574, 2011 IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, 11/6/11. https://doi.org/10.1109/ICCV.2011.6126416
Min D, Lu J, Do MN. A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy? In 2011 International Conference on Computer Vision, ICCV 2011. 2011. p. 1567-1574. 6126416 https://doi.org/10.1109/ICCV.2011.6126416
Min, Dongbo ; Lu, Jiangbo ; Do, Minh N. / A revisit to cost aggregation in stereo matching : How far can we reduce its computational redundancy?. 2011 International Conference on Computer Vision, ICCV 2011. 2011. pp. 1567-1574
@inproceedings{63b4697586944121b0dcf09dc328a5ec,
title = "A revisit to cost aggregation in stereo matching: How far can we reduce its computational redundancy?",
abstract = "This paper presents a novel method for performing an efficient cost aggregation in stereo matching. The cost aggregation problem is re-formulated with a perspective of a histogram, and it gives us a potential to reduce the complexity of the cost aggregation significantly. Different from the previous methods which have tried to reduce the complexity in terms of the size of an image and a matching window, our approach focuses on reducing the computational redundancy which exists among the search range, caused by a repeated filtering for all disparity hypotheses. Moreover, we also reduce the complexity of the window-based filtering through an efficient sampling scheme inside the matching window. The trade-off between accuracy and complexity is extensively investigated into parameters used in the proposed method. Experimental results show that the proposed method provides high-quality disparity maps with low complexity. This work provides new insights into complexity-constrained stereo matching algorithm design.",
author = "Dongbo Min and Jiangbo Lu and Do, {Minh N}",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/ICCV.2011.6126416",
language = "English (US)",
isbn = "9781457711015",
pages = "1567--1574",
booktitle = "2011 International Conference on Computer Vision, ICCV 2011",

}

TY - GEN

T1 - A revisit to cost aggregation in stereo matching

T2 - How far can we reduce its computational redundancy?

AU - Min, Dongbo

AU - Lu, Jiangbo

AU - Do, Minh N

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This paper presents a novel method for performing an efficient cost aggregation in stereo matching. The cost aggregation problem is re-formulated with a perspective of a histogram, and it gives us a potential to reduce the complexity of the cost aggregation significantly. Different from the previous methods which have tried to reduce the complexity in terms of the size of an image and a matching window, our approach focuses on reducing the computational redundancy which exists among the search range, caused by a repeated filtering for all disparity hypotheses. Moreover, we also reduce the complexity of the window-based filtering through an efficient sampling scheme inside the matching window. The trade-off between accuracy and complexity is extensively investigated into parameters used in the proposed method. Experimental results show that the proposed method provides high-quality disparity maps with low complexity. This work provides new insights into complexity-constrained stereo matching algorithm design.

AB - This paper presents a novel method for performing an efficient cost aggregation in stereo matching. The cost aggregation problem is re-formulated with a perspective of a histogram, and it gives us a potential to reduce the complexity of the cost aggregation significantly. Different from the previous methods which have tried to reduce the complexity in terms of the size of an image and a matching window, our approach focuses on reducing the computational redundancy which exists among the search range, caused by a repeated filtering for all disparity hypotheses. Moreover, we also reduce the complexity of the window-based filtering through an efficient sampling scheme inside the matching window. The trade-off between accuracy and complexity is extensively investigated into parameters used in the proposed method. Experimental results show that the proposed method provides high-quality disparity maps with low complexity. This work provides new insights into complexity-constrained stereo matching algorithm design.

UR - http://www.scopus.com/inward/record.url?scp=84863011842&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863011842&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2011.6126416

DO - 10.1109/ICCV.2011.6126416

M3 - Conference contribution

SN - 9781457711015

SP - 1567

EP - 1574

BT - 2011 International Conference on Computer Vision, ICCV 2011

ER -