Robust depth enhancement based on texture and depth consistency

Ting An Chang, Wei Chen Liao, Jar-Ferr Yang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

With advances in three-dimension television (3DTV) technology, accurate depth information for 3DTV broadcasting has gained much attention recently. The depth map, either retrieved by stereo matching or captured by the RGB-D camera, is mostly with lower resolution and often with noisy or missing values than the texture frame. How to effectively utilise high-resolution texture image to enhance the corresponding depth map becomes an important and inevitable approach. In this study, the authors propose texture similarity-based hole filling, texture similarity-based depth enhancement and rotating counsel depth refinement to enhance the depth map. Thus, the proposed depth enhancement system could suppress the noise, fill the holes and sharpen the object edges simultaneously. Experimental results demonstrate that the proposed system provides a superior performance, especially around the object boundary comparing to the state-of-the-art depth enhancement methods.

Original languageEnglish
Pages (from-to)119-128
Number of pages10
JournalIET Signal Processing
Volume12
Issue number1
DOIs
Publication statusPublished - 2018 Feb 1

Fingerprint

Textures
Broadcasting
Television
Cameras

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Chang, Ting An ; Liao, Wei Chen ; Yang, Jar-Ferr. / Robust depth enhancement based on texture and depth consistency. In: IET Signal Processing. 2018 ; Vol. 12, No. 1. pp. 119-128.
@article{d5a45ad463544fe88645e1797099cc7d,
title = "Robust depth enhancement based on texture and depth consistency",
abstract = "With advances in three-dimension television (3DTV) technology, accurate depth information for 3DTV broadcasting has gained much attention recently. The depth map, either retrieved by stereo matching or captured by the RGB-D camera, is mostly with lower resolution and often with noisy or missing values than the texture frame. How to effectively utilise high-resolution texture image to enhance the corresponding depth map becomes an important and inevitable approach. In this study, the authors propose texture similarity-based hole filling, texture similarity-based depth enhancement and rotating counsel depth refinement to enhance the depth map. Thus, the proposed depth enhancement system could suppress the noise, fill the holes and sharpen the object edges simultaneously. Experimental results demonstrate that the proposed system provides a superior performance, especially around the object boundary comparing to the state-of-the-art depth enhancement methods.",
author = "Chang, {Ting An} and Liao, {Wei Chen} and Jar-Ferr Yang",
year = "2018",
month = "2",
day = "1",
doi = "10.1049/iet-spr.2016.0550",
language = "English",
volume = "12",
pages = "119--128",
journal = "IET Signal Processing",
issn = "1751-9675",
publisher = "Institution of Engineering and Technology",
number = "1",

}

Robust depth enhancement based on texture and depth consistency. / Chang, Ting An; Liao, Wei Chen; Yang, Jar-Ferr.

In: IET Signal Processing, Vol. 12, No. 1, 01.02.2018, p. 119-128.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Robust depth enhancement based on texture and depth consistency

AU - Chang, Ting An

AU - Liao, Wei Chen

AU - Yang, Jar-Ferr

PY - 2018/2/1

Y1 - 2018/2/1

N2 - With advances in three-dimension television (3DTV) technology, accurate depth information for 3DTV broadcasting has gained much attention recently. The depth map, either retrieved by stereo matching or captured by the RGB-D camera, is mostly with lower resolution and often with noisy or missing values than the texture frame. How to effectively utilise high-resolution texture image to enhance the corresponding depth map becomes an important and inevitable approach. In this study, the authors propose texture similarity-based hole filling, texture similarity-based depth enhancement and rotating counsel depth refinement to enhance the depth map. Thus, the proposed depth enhancement system could suppress the noise, fill the holes and sharpen the object edges simultaneously. Experimental results demonstrate that the proposed system provides a superior performance, especially around the object boundary comparing to the state-of-the-art depth enhancement methods.

AB - With advances in three-dimension television (3DTV) technology, accurate depth information for 3DTV broadcasting has gained much attention recently. The depth map, either retrieved by stereo matching or captured by the RGB-D camera, is mostly with lower resolution and often with noisy or missing values than the texture frame. How to effectively utilise high-resolution texture image to enhance the corresponding depth map becomes an important and inevitable approach. In this study, the authors propose texture similarity-based hole filling, texture similarity-based depth enhancement and rotating counsel depth refinement to enhance the depth map. Thus, the proposed depth enhancement system could suppress the noise, fill the holes and sharpen the object edges simultaneously. Experimental results demonstrate that the proposed system provides a superior performance, especially around the object boundary comparing to the state-of-the-art depth enhancement methods.

UR - http://www.scopus.com/inward/record.url?scp=85041658990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041658990&partnerID=8YFLogxK

U2 - 10.1049/iet-spr.2016.0550

DO - 10.1049/iet-spr.2016.0550

M3 - Article

AN - SCOPUS:85041658990

VL - 12

SP - 119

EP - 128

JO - IET Signal Processing

JF - IET Signal Processing

SN - 1751-9675

IS - 1

ER -