A depth-aware character generator for 3DTV

Juhyun Oh, Kwanghoon Sohn

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In 3DTV, it is known that video captions and graphics should be inserted at proper scene depth positions, to prevent possible viewing discomfort. We propose a character generator that automatically analyzes the scene disparities and determines the proper depth of the graphic object to be inserted. The challenge is that the disparity range estimation from feature correspondences is severely affected even by a few outliers, whereas nauml;ve SURF or BRIEF matching produces a considerable amount of outliers. We propose a multiple-hypothesis feature matching algorithm that considers the disparity coherence between adjacent features, with which most mismatches can be removed according to the reliability aggregated from the neighboring features. To estimate the accurate disparity range from the feature correspondences, a disparity histogram is computed and filtered by a space-time kernel to suppress the effect of incorrect disparities. We also propose the disparity-depth conversion in the asymmetric view frustum which is used for the stereoscopic rendering of graphics. Experimental results show that a 3D graphic object is successfully inserted at the desired depth which is obtained from the proposed disparity range estimation and disparity-depth conversion.

Original languageEnglish
Article number6256762
Pages (from-to)523-532
Number of pages10
JournalIEEE Transactions on Broadcasting
Volume58
Issue number4
DOIs
Publication statusPublished - 2012 Jan 1

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

@article{7862ae033b2d44a8a71dcd0b3c5db40d,
title = "A depth-aware character generator for 3DTV",
abstract = "In 3DTV, it is known that video captions and graphics should be inserted at proper scene depth positions, to prevent possible viewing discomfort. We propose a character generator that automatically analyzes the scene disparities and determines the proper depth of the graphic object to be inserted. The challenge is that the disparity range estimation from feature correspondences is severely affected even by a few outliers, whereas nauml;ve SURF or BRIEF matching produces a considerable amount of outliers. We propose a multiple-hypothesis feature matching algorithm that considers the disparity coherence between adjacent features, with which most mismatches can be removed according to the reliability aggregated from the neighboring features. To estimate the accurate disparity range from the feature correspondences, a disparity histogram is computed and filtered by a space-time kernel to suppress the effect of incorrect disparities. We also propose the disparity-depth conversion in the asymmetric view frustum which is used for the stereoscopic rendering of graphics. Experimental results show that a 3D graphic object is successfully inserted at the desired depth which is obtained from the proposed disparity range estimation and disparity-depth conversion.",
author = "Juhyun Oh and Kwanghoon Sohn",
year = "2012",
month = "1",
day = "1",
doi = "10.1109/TBC.2012.2204942",
language = "English",
volume = "58",
pages = "523--532",
journal = "IEEE Transactions on Broadcasting",
issn = "0018-9316",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

A depth-aware character generator for 3DTV. / Oh, Juhyun; Sohn, Kwanghoon.

In: IEEE Transactions on Broadcasting, Vol. 58, No. 4, 6256762, 01.01.2012, p. 523-532.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A depth-aware character generator for 3DTV

AU - Oh, Juhyun

AU - Sohn, Kwanghoon

PY - 2012/1/1

Y1 - 2012/1/1

N2 - In 3DTV, it is known that video captions and graphics should be inserted at proper scene depth positions, to prevent possible viewing discomfort. We propose a character generator that automatically analyzes the scene disparities and determines the proper depth of the graphic object to be inserted. The challenge is that the disparity range estimation from feature correspondences is severely affected even by a few outliers, whereas nauml;ve SURF or BRIEF matching produces a considerable amount of outliers. We propose a multiple-hypothesis feature matching algorithm that considers the disparity coherence between adjacent features, with which most mismatches can be removed according to the reliability aggregated from the neighboring features. To estimate the accurate disparity range from the feature correspondences, a disparity histogram is computed and filtered by a space-time kernel to suppress the effect of incorrect disparities. We also propose the disparity-depth conversion in the asymmetric view frustum which is used for the stereoscopic rendering of graphics. Experimental results show that a 3D graphic object is successfully inserted at the desired depth which is obtained from the proposed disparity range estimation and disparity-depth conversion.

AB - In 3DTV, it is known that video captions and graphics should be inserted at proper scene depth positions, to prevent possible viewing discomfort. We propose a character generator that automatically analyzes the scene disparities and determines the proper depth of the graphic object to be inserted. The challenge is that the disparity range estimation from feature correspondences is severely affected even by a few outliers, whereas nauml;ve SURF or BRIEF matching produces a considerable amount of outliers. We propose a multiple-hypothesis feature matching algorithm that considers the disparity coherence between adjacent features, with which most mismatches can be removed according to the reliability aggregated from the neighboring features. To estimate the accurate disparity range from the feature correspondences, a disparity histogram is computed and filtered by a space-time kernel to suppress the effect of incorrect disparities. We also propose the disparity-depth conversion in the asymmetric view frustum which is used for the stereoscopic rendering of graphics. Experimental results show that a 3D graphic object is successfully inserted at the desired depth which is obtained from the proposed disparity range estimation and disparity-depth conversion.

UR - http://www.scopus.com/inward/record.url?scp=84870292994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870292994&partnerID=8YFLogxK

U2 - 10.1109/TBC.2012.2204942

DO - 10.1109/TBC.2012.2204942

M3 - Article

AN - SCOPUS:84870292994

VL - 58

SP - 523

EP - 532

JO - IEEE Transactions on Broadcasting

JF - IEEE Transactions on Broadcasting

SN - 0018-9316

IS - 4

M1 - 6256762

ER -