Hierarchical stereo matching via color segmentation

Takashi Kudo, Keiichiro Shirai, Masaaki Ikehara

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

3 Citations (Scopus)

Abstract

This paper presents a new segment-based stereo matching algorithm using a coarse-to-fine multiresolution strategy. In general, the multiresolution scheme was employed in a direct descending optimization to avoid matching in the local minimal. However, it is not effective in homogeneously textured regions and disparity discontinuous boundaries. We implement a novel hierarchical segment-based matching scheme to produce accurate disparity maps, which resolves the above mentioned challenging problems. We utilize the hierarchical color segmentation that is classified in each resolution level to guide the matching process gradually. The principal feature of our scheme is to combine the local and the global optimization in multiresolution stages. To validate the proposed algorithm, we show the experimental results on the new Middlebury database sets.

Original languageEnglish
Title of host publication2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop
Pages522-525
Number of pages4
DOIs
Publication statusPublished - 2006
Event2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop, DSPWS - Moose, WY, United States
Duration: 2006 Sep 242006 Sep 27

Other

Other2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop, DSPWS
CountryUnited States
CityMoose, WY
Period06/9/2406/9/27

Fingerprint

Color
Global optimization

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Kudo, T., Shirai, K., & Ikehara, M. (2006). Hierarchical stereo matching via color segmentation. In 2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop (pp. 522-525). [4041119] https://doi.org/10.1109/DSPWS.2006.265478

Hierarchical stereo matching via color segmentation. / Kudo, Takashi; Shirai, Keiichiro; Ikehara, Masaaki.

2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop. 2006. p. 522-525 4041119.

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

Kudo, T, Shirai, K & Ikehara, M 2006, Hierarchical stereo matching via color segmentation. in 2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop., 4041119, pp. 522-525, 2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop, DSPWS, Moose, WY, United States, 06/9/24. https://doi.org/10.1109/DSPWS.2006.265478
Kudo T, Shirai K, Ikehara M. Hierarchical stereo matching via color segmentation. In 2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop. 2006. p. 522-525. 4041119 https://doi.org/10.1109/DSPWS.2006.265478
Kudo, Takashi ; Shirai, Keiichiro ; Ikehara, Masaaki. / Hierarchical stereo matching via color segmentation. 2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop. 2006. pp. 522-525
@inproceedings{7cae29a75269436e947d77abd982d80d,
title = "Hierarchical stereo matching via color segmentation",
abstract = "This paper presents a new segment-based stereo matching algorithm using a coarse-to-fine multiresolution strategy. In general, the multiresolution scheme was employed in a direct descending optimization to avoid matching in the local minimal. However, it is not effective in homogeneously textured regions and disparity discontinuous boundaries. We implement a novel hierarchical segment-based matching scheme to produce accurate disparity maps, which resolves the above mentioned challenging problems. We utilize the hierarchical color segmentation that is classified in each resolution level to guide the matching process gradually. The principal feature of our scheme is to combine the local and the global optimization in multiresolution stages. To validate the proposed algorithm, we show the experimental results on the new Middlebury database sets.",
author = "Takashi Kudo and Keiichiro Shirai and Masaaki Ikehara",
year = "2006",
doi = "10.1109/DSPWS.2006.265478",
language = "English",
pages = "522--525",
booktitle = "2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop",

}

TY - GEN

T1 - Hierarchical stereo matching via color segmentation

AU - Kudo, Takashi

AU - Shirai, Keiichiro

AU - Ikehara, Masaaki

PY - 2006

Y1 - 2006

N2 - This paper presents a new segment-based stereo matching algorithm using a coarse-to-fine multiresolution strategy. In general, the multiresolution scheme was employed in a direct descending optimization to avoid matching in the local minimal. However, it is not effective in homogeneously textured regions and disparity discontinuous boundaries. We implement a novel hierarchical segment-based matching scheme to produce accurate disparity maps, which resolves the above mentioned challenging problems. We utilize the hierarchical color segmentation that is classified in each resolution level to guide the matching process gradually. The principal feature of our scheme is to combine the local and the global optimization in multiresolution stages. To validate the proposed algorithm, we show the experimental results on the new Middlebury database sets.

AB - This paper presents a new segment-based stereo matching algorithm using a coarse-to-fine multiresolution strategy. In general, the multiresolution scheme was employed in a direct descending optimization to avoid matching in the local minimal. However, it is not effective in homogeneously textured regions and disparity discontinuous boundaries. We implement a novel hierarchical segment-based matching scheme to produce accurate disparity maps, which resolves the above mentioned challenging problems. We utilize the hierarchical color segmentation that is classified in each resolution level to guide the matching process gradually. The principal feature of our scheme is to combine the local and the global optimization in multiresolution stages. To validate the proposed algorithm, we show the experimental results on the new Middlebury database sets.

UR - http://www.scopus.com/inward/record.url?scp=39049173148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=39049173148&partnerID=8YFLogxK

U2 - 10.1109/DSPWS.2006.265478

DO - 10.1109/DSPWS.2006.265478

M3 - Conference contribution

AN - SCOPUS:39049173148

SP - 522

EP - 525

BT - 2006 IEEE 12th Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop

ER -