Automatic 2D-To-3D video conversion technique based on depth-from-motion and color segmentation

Lai-Man Po; Xuyuan Xu; Yuesheng Zhu; Shihang Zhang; Kwok-Wai Cheung; Chi-Wang Ting

doi:10.1109/ICOSP.2010.5655850

Automatic 2D-To-3D video conversion technique based on depth-from-motion and color segmentation

Lai-Man Po, Xuyuan Xu, Yuesheng Zhu, Shihang Zhang, Kwok-Wai Cheung, Chi-Wang Ting

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

17 Citations (Scopus)

Abstract

Most of the TV manufacturers have released 3DTVs in the summer of 2010 using shutter-glasses technology. 3D video applications are becoming popular in our daily life, especially at home entertainment. Although more and more 3D movies are being made, 3D video contents are still not rich enough to satisfy the future 3D video market. There is a rising demand on new techniques for automatically converting 2D video content to stereoscopic 3D video displays. In this paper, an automatic monoscopic video to stereoscopic 3D video conversion scheme is presented using block-based depth from motion estimation and color segmentation for depth map enhancement. The color based region segmentation provides good region boundary information, which is used to fuse with block-based depth map for eliminating the staircase effect and assigning good depth value in each segmented region. The experimental results show that this scheme can achieve relatively high quality 3D stereoscopic video output. © 2010 IEEE.

Original language	English
Title of host publication	International Conference on Signal Processing Proceedings, ICSP
Pages	1000-1003
DOIs	https://doi.org/10.1109/ICOSP.2010.5655850
Publication status	Published - 2010
Event	2010 IEEE 10th International Conference on Signal Processing, ICSP2010 - Beijing, China Duration: 24 Oct 2010 → 28 Oct 2010

Conference

Conference	2010 IEEE 10th International Conference on Signal Processing, ICSP2010
Country/Territory	China
City	Beijing
Period	24/10/10 → 28/10/10

Research Keywords

3D-TV
Color segmentation
Depth from Motion
Stereo vision

Access Output

10.1109/ICOSP.2010.5655850

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{eaa69352e8c142519ce26fe00df9c7b8,

title = "Automatic 2D-To-3D video conversion technique based on depth-from-motion and color segmentation",

abstract = "Most of the TV manufacturers have released 3DTVs in the summer of 2010 using shutter-glasses technology. 3D video applications are becoming popular in our daily life, especially at home entertainment. Although more and more 3D movies are being made, 3D video contents are still not rich enough to satisfy the future 3D video market. There is a rising demand on new techniques for automatically converting 2D video content to stereoscopic 3D video displays. In this paper, an automatic monoscopic video to stereoscopic 3D video conversion scheme is presented using block-based depth from motion estimation and color segmentation for depth map enhancement. The color based region segmentation provides good region boundary information, which is used to fuse with block-based depth map for eliminating the staircase effect and assigning good depth value in each segmented region. The experimental results show that this scheme can achieve relatively high quality 3D stereoscopic video output. {\textcopyright} 2010 IEEE.",

keywords = "3D-TV, Color segmentation, Depth from Motion, Stereo vision",

author = "Lai-Man Po and Xuyuan Xu and Yuesheng Zhu and Shihang Zhang and Kwok-Wai Cheung and Chi-Wang Ting",

year = "2010",

doi = "10.1109/ICOSP.2010.5655850",

language = "English",

isbn = "9781424458981",

pages = "1000--1003",

booktitle = "International Conference on Signal Processing Proceedings, ICSP",

note = "2010 IEEE 10th International Conference on Signal Processing, ICSP2010 ; Conference date: 24-10-2010 Through 28-10-2010",

}

Po, L-M, Xu, X, Zhu, Y, Zhang, S, Cheung, K-W & Ting, C-W 2010, Automatic 2D-To-3D video conversion technique based on depth-from-motion and color segmentation. in International Conference on Signal Processing Proceedings, ICSP., 5655850, pp. 1000-1003, 2010 IEEE 10th International Conference on Signal Processing, ICSP2010, Beijing, China, 24/10/10. https://doi.org/10.1109/ICOSP.2010.5655850

Automatic 2D-To-3D video conversion technique based on depth-from-motion and color segmentation. / Po, Lai-Man; Xu, Xuyuan; Zhu, Yuesheng et al.
International Conference on Signal Processing Proceedings, ICSP. 2010. p. 1000-1003 5655850.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Automatic 2D-To-3D video conversion technique based on depth-from-motion and color segmentation

AU - Po, Lai-Man

AU - Xu, Xuyuan

AU - Zhu, Yuesheng

AU - Zhang, Shihang

AU - Cheung, Kwok-Wai

AU - Ting, Chi-Wang

PY - 2010

Y1 - 2010

N2 - Most of the TV manufacturers have released 3DTVs in the summer of 2010 using shutter-glasses technology. 3D video applications are becoming popular in our daily life, especially at home entertainment. Although more and more 3D movies are being made, 3D video contents are still not rich enough to satisfy the future 3D video market. There is a rising demand on new techniques for automatically converting 2D video content to stereoscopic 3D video displays. In this paper, an automatic monoscopic video to stereoscopic 3D video conversion scheme is presented using block-based depth from motion estimation and color segmentation for depth map enhancement. The color based region segmentation provides good region boundary information, which is used to fuse with block-based depth map for eliminating the staircase effect and assigning good depth value in each segmented region. The experimental results show that this scheme can achieve relatively high quality 3D stereoscopic video output. © 2010 IEEE.

AB - Most of the TV manufacturers have released 3DTVs in the summer of 2010 using shutter-glasses technology. 3D video applications are becoming popular in our daily life, especially at home entertainment. Although more and more 3D movies are being made, 3D video contents are still not rich enough to satisfy the future 3D video market. There is a rising demand on new techniques for automatically converting 2D video content to stereoscopic 3D video displays. In this paper, an automatic monoscopic video to stereoscopic 3D video conversion scheme is presented using block-based depth from motion estimation and color segmentation for depth map enhancement. The color based region segmentation provides good region boundary information, which is used to fuse with block-based depth map for eliminating the staircase effect and assigning good depth value in each segmented region. The experimental results show that this scheme can achieve relatively high quality 3D stereoscopic video output. © 2010 IEEE.

KW - 3D-TV

KW - Color segmentation

KW - Depth from Motion

KW - Stereo vision

UR - http://www.scopus.com/inward/record.url?scp=78651078448&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-78651078448&origin=recordpage

U2 - 10.1109/ICOSP.2010.5655850

DO - 10.1109/ICOSP.2010.5655850

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781424458981

SP - 1000

EP - 1003

BT - International Conference on Signal Processing Proceedings, ICSP

T2 - 2010 IEEE 10th International Conference on Signal Processing, ICSP2010

Y2 - 24 October 2010 through 28 October 2010

ER -

Automatic 2D-To-3D video conversion technique based on depth-from-motion and color segmentation

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this