Depth image interpolation with the propagation of color geodesic neighborhoods

Kiyoshi Matsuo, Yoshimitsu Aoki

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

Abstract

This paper describes a new accurate interpolation method of a low-resolution depth image using a high-resolution color image for the structural analysis of 3d data. Our method adopts the strategy to detect and omit regions where it is difficult to estimate depth value accurately. In order to achieve this, Color geodesic neighborhood is used as the local smooth surface, and depth data is interpolated with checking smoothness of connections between them. Pixels where they can not be smoothly connected are omitted automatically as indeterminable pixels in this process. Experiments with images of the Middlebury stereo datasets demonstrate that in the quantitative sense our method can interpolate depth images more accurately than other interpolation methods.

Original languageEnglish
Title of host publication2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013
DOIs
Publication statusPublished - 2013
Event2013 2nd International Conference on Informatics, Electronics and Vision, ICIEV 2013 - Dhaka, Bangladesh
Duration: 2013 May 172013 May 18

Other

Other2013 2nd International Conference on Informatics, Electronics and Vision, ICIEV 2013
CountryBangladesh
CityDhaka
Period13/5/1713/5/18

Fingerprint

Interpolation
Pixels
Color
Structural analysis
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Matsuo, K., & Aoki, Y. (2013). Depth image interpolation with the propagation of color geodesic neighborhoods. In 2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013 [6572627] https://doi.org/10.1109/ICIEV.2013.6572627

Depth image interpolation with the propagation of color geodesic neighborhoods. / Matsuo, Kiyoshi; Aoki, Yoshimitsu.

2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013. 2013. 6572627.

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

Matsuo, K & Aoki, Y 2013, Depth image interpolation with the propagation of color geodesic neighborhoods. in 2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013., 6572627, 2013 2nd International Conference on Informatics, Electronics and Vision, ICIEV 2013, Dhaka, Bangladesh, 13/5/17. https://doi.org/10.1109/ICIEV.2013.6572627
Matsuo K, Aoki Y. Depth image interpolation with the propagation of color geodesic neighborhoods. In 2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013. 2013. 6572627 https://doi.org/10.1109/ICIEV.2013.6572627
Matsuo, Kiyoshi ; Aoki, Yoshimitsu. / Depth image interpolation with the propagation of color geodesic neighborhoods. 2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013. 2013.
@inproceedings{42fdb19def96400dbd271b2b8642aad8,
title = "Depth image interpolation with the propagation of color geodesic neighborhoods",
abstract = "This paper describes a new accurate interpolation method of a low-resolution depth image using a high-resolution color image for the structural analysis of 3d data. Our method adopts the strategy to detect and omit regions where it is difficult to estimate depth value accurately. In order to achieve this, Color geodesic neighborhood is used as the local smooth surface, and depth data is interpolated with checking smoothness of connections between them. Pixels where they can not be smoothly connected are omitted automatically as indeterminable pixels in this process. Experiments with images of the Middlebury stereo datasets demonstrate that in the quantitative sense our method can interpolate depth images more accurately than other interpolation methods.",
author = "Kiyoshi Matsuo and Yoshimitsu Aoki",
year = "2013",
doi = "10.1109/ICIEV.2013.6572627",
language = "English",
isbn = "9781479903979",
booktitle = "2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013",

}

TY - GEN

T1 - Depth image interpolation with the propagation of color geodesic neighborhoods

AU - Matsuo, Kiyoshi

AU - Aoki, Yoshimitsu

PY - 2013

Y1 - 2013

N2 - This paper describes a new accurate interpolation method of a low-resolution depth image using a high-resolution color image for the structural analysis of 3d data. Our method adopts the strategy to detect and omit regions where it is difficult to estimate depth value accurately. In order to achieve this, Color geodesic neighborhood is used as the local smooth surface, and depth data is interpolated with checking smoothness of connections between them. Pixels where they can not be smoothly connected are omitted automatically as indeterminable pixels in this process. Experiments with images of the Middlebury stereo datasets demonstrate that in the quantitative sense our method can interpolate depth images more accurately than other interpolation methods.

AB - This paper describes a new accurate interpolation method of a low-resolution depth image using a high-resolution color image for the structural analysis of 3d data. Our method adopts the strategy to detect and omit regions where it is difficult to estimate depth value accurately. In order to achieve this, Color geodesic neighborhood is used as the local smooth surface, and depth data is interpolated with checking smoothness of connections between them. Pixels where they can not be smoothly connected are omitted automatically as indeterminable pixels in this process. Experiments with images of the Middlebury stereo datasets demonstrate that in the quantitative sense our method can interpolate depth images more accurately than other interpolation methods.

UR - http://www.scopus.com/inward/record.url?scp=84883316252&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883316252&partnerID=8YFLogxK

U2 - 10.1109/ICIEV.2013.6572627

DO - 10.1109/ICIEV.2013.6572627

M3 - Conference contribution

SN - 9781479903979

BT - 2013 International Conference on Informatics, Electronics and Vision, ICIEV 2013

ER -