Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods

Kiyoshi Matsuo, Yoshimitsu Aoki

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

Abstract

This paper describes an iterative procedure of accurate depth interpolation for a low-resolution depth image using a high-resolution color image. In our procedure, depth interpolation is gradually achieved with generating smooth junctions of similar color regions. These junctions give the segmentation of the interpolated region and we use this information to interpolate depth value on each segment, and to promote the generation of junctions additionally. In experiments with images of the Middlebury stereo datasets, our procedure interpolates each image at a high rate, and achieves the low error compared with previous methods.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages2116-2121
Number of pages6
Publication statusPublished - 2013
Event2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, Japan
Duration: 2013 Sep 142013 Sep 17

Other

Other2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013
CountryJapan
CityNagoya
Period13/9/1413/9/17

Fingerprint

Interpolation
Color
Information use
Experiments

Keywords

  • Depth image interpolation
  • Geodesic distance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Matsuo, K., & Aoki, Y. (2013). Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods. In Proceedings of the SICE Annual Conference (pp. 2116-2121)

Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods. / Matsuo, Kiyoshi; Aoki, Yoshimitsu.

Proceedings of the SICE Annual Conference. 2013. p. 2116-2121.

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

Matsuo, K & Aoki, Y 2013, Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods. in Proceedings of the SICE Annual Conference. pp. 2116-2121, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, Japan, 13/9/14.
Matsuo K, Aoki Y. Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods. In Proceedings of the SICE Annual Conference. 2013. p. 2116-2121
Matsuo, Kiyoshi ; Aoki, Yoshimitsu. / Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods. Proceedings of the SICE Annual Conference. 2013. pp. 2116-2121
@inproceedings{ecefa47f26924e0888394f3e4c2f3e1d,
title = "Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods",
abstract = "This paper describes an iterative procedure of accurate depth interpolation for a low-resolution depth image using a high-resolution color image. In our procedure, depth interpolation is gradually achieved with generating smooth junctions of similar color regions. These junctions give the segmentation of the interpolated region and we use this information to interpolate depth value on each segment, and to promote the generation of junctions additionally. In experiments with images of the Middlebury stereo datasets, our procedure interpolates each image at a high rate, and achieves the low error compared with previous methods.",
keywords = "Depth image interpolation, Geodesic distance",
author = "Kiyoshi Matsuo and Yoshimitsu Aoki",
year = "2013",
language = "English",
pages = "2116--2121",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Depth interpolation via segmentation defined from smooth junctions of color geodesic neighborhoods

AU - Matsuo, Kiyoshi

AU - Aoki, Yoshimitsu

PY - 2013

Y1 - 2013

N2 - This paper describes an iterative procedure of accurate depth interpolation for a low-resolution depth image using a high-resolution color image. In our procedure, depth interpolation is gradually achieved with generating smooth junctions of similar color regions. These junctions give the segmentation of the interpolated region and we use this information to interpolate depth value on each segment, and to promote the generation of junctions additionally. In experiments with images of the Middlebury stereo datasets, our procedure interpolates each image at a high rate, and achieves the low error compared with previous methods.

AB - This paper describes an iterative procedure of accurate depth interpolation for a low-resolution depth image using a high-resolution color image. In our procedure, depth interpolation is gradually achieved with generating smooth junctions of similar color regions. These junctions give the segmentation of the interpolated region and we use this information to interpolate depth value on each segment, and to promote the generation of junctions additionally. In experiments with images of the Middlebury stereo datasets, our procedure interpolates each image at a high rate, and achieves the low error compared with previous methods.

KW - Depth image interpolation

KW - Geodesic distance

UR - http://www.scopus.com/inward/record.url?scp=84888589222&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888589222&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84888589222

SP - 2116

EP - 2121

BT - Proceedings of the SICE Annual Conference

ER -