A novel depth image enhancement method based on the linear surface model

Seok Jae Kang, Mun Cheon Kang, Dae Hwan Kim, Sung-Jea Ko

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In three-dimensional (3D) video applications, structured-light RGB-D cameras are commonly used to capture depth images that convey the per-pixel depth information in a scene. However, these cameras often produce regions with missing pixels (MPs). These regions, referred to as holes, will not contain no any depth information for the captured depth image. In this paper, a novel depth image enhancement method that accurately estimates depth values of MPs is presented. In the proposed method, the neighboring region outside the hole is first segmented into superpixels using simple linear iterative clustering. Subsequently, the depth value trend of each superpixel is modeled as a linear surface. Finally, one of the linear surfaces is selected using a proposed metric, to estimate the depth value of a particular MP in the hole. Experimental results demonstrate that the proposed method provides superior performance, especially around the object boundary, compared with other state-of-theart depth image enhancement methods1.

Original languageEnglish
Article number7027347
Pages (from-to)710-718
Number of pages9
JournalIEEE Transactions on Consumer Electronics
Volume60
Issue number4
DOIs
Publication statusPublished - 2014 Nov 1

Fingerprint

Image enhancement
Pixels
Cameras

Keywords

  • Depth image enhancement
  • hole filling
  • least squares method
  • linear surface model
  • piecewise linear approximation
  • structured-light RGB-D camera

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

A novel depth image enhancement method based on the linear surface model. / Kang, Seok Jae; Kang, Mun Cheon; Kim, Dae Hwan; Ko, Sung-Jea.

In: IEEE Transactions on Consumer Electronics, Vol. 60, No. 4, 7027347, 01.11.2014, p. 710-718.

Research output: Contribution to journalArticle

Kang, Seok Jae ; Kang, Mun Cheon ; Kim, Dae Hwan ; Ko, Sung-Jea. / A novel depth image enhancement method based on the linear surface model. In: IEEE Transactions on Consumer Electronics. 2014 ; Vol. 60, No. 4. pp. 710-718.
@article{4484bd5512814041a13a7413514637aa,
title = "A novel depth image enhancement method based on the linear surface model",
abstract = "In three-dimensional (3D) video applications, structured-light RGB-D cameras are commonly used to capture depth images that convey the per-pixel depth information in a scene. However, these cameras often produce regions with missing pixels (MPs). These regions, referred to as holes, will not contain no any depth information for the captured depth image. In this paper, a novel depth image enhancement method that accurately estimates depth values of MPs is presented. In the proposed method, the neighboring region outside the hole is first segmented into superpixels using simple linear iterative clustering. Subsequently, the depth value trend of each superpixel is modeled as a linear surface. Finally, one of the linear surfaces is selected using a proposed metric, to estimate the depth value of a particular MP in the hole. Experimental results demonstrate that the proposed method provides superior performance, especially around the object boundary, compared with other state-of-theart depth image enhancement methods1.",
keywords = "Depth image enhancement, hole filling, least squares method, linear surface model, piecewise linear approximation, structured-light RGB-D camera",
author = "Kang, {Seok Jae} and Kang, {Mun Cheon} and Kim, {Dae Hwan} and Sung-Jea Ko",
year = "2014",
month = "11",
day = "1",
doi = "10.1109/TCE.2014.7027347",
language = "English",
volume = "60",
pages = "710--718",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - A novel depth image enhancement method based on the linear surface model

AU - Kang, Seok Jae

AU - Kang, Mun Cheon

AU - Kim, Dae Hwan

AU - Ko, Sung-Jea

PY - 2014/11/1

Y1 - 2014/11/1

N2 - In three-dimensional (3D) video applications, structured-light RGB-D cameras are commonly used to capture depth images that convey the per-pixel depth information in a scene. However, these cameras often produce regions with missing pixels (MPs). These regions, referred to as holes, will not contain no any depth information for the captured depth image. In this paper, a novel depth image enhancement method that accurately estimates depth values of MPs is presented. In the proposed method, the neighboring region outside the hole is first segmented into superpixels using simple linear iterative clustering. Subsequently, the depth value trend of each superpixel is modeled as a linear surface. Finally, one of the linear surfaces is selected using a proposed metric, to estimate the depth value of a particular MP in the hole. Experimental results demonstrate that the proposed method provides superior performance, especially around the object boundary, compared with other state-of-theart depth image enhancement methods1.

AB - In three-dimensional (3D) video applications, structured-light RGB-D cameras are commonly used to capture depth images that convey the per-pixel depth information in a scene. However, these cameras often produce regions with missing pixels (MPs). These regions, referred to as holes, will not contain no any depth information for the captured depth image. In this paper, a novel depth image enhancement method that accurately estimates depth values of MPs is presented. In the proposed method, the neighboring region outside the hole is first segmented into superpixels using simple linear iterative clustering. Subsequently, the depth value trend of each superpixel is modeled as a linear surface. Finally, one of the linear surfaces is selected using a proposed metric, to estimate the depth value of a particular MP in the hole. Experimental results demonstrate that the proposed method provides superior performance, especially around the object boundary, compared with other state-of-theart depth image enhancement methods1.

KW - Depth image enhancement

KW - hole filling

KW - least squares method

KW - linear surface model

KW - piecewise linear approximation

KW - structured-light RGB-D camera

UR - http://www.scopus.com/inward/record.url?scp=84923780345&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923780345&partnerID=8YFLogxK

U2 - 10.1109/TCE.2014.7027347

DO - 10.1109/TCE.2014.7027347

M3 - Article

VL - 60

SP - 710

EP - 718

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 4

M1 - 7027347

ER -