Publication detail

On-line Video Synchronization Based on Visual Vocabularies

BERAN, V. HEROUT, A. ZEMČÍK, P.

Original Title

On-line Video Synchronization Based on Visual Vocabularies

English Title

On-line Video Synchronization Based on Visual Vocabularies

Type

conference paper

Language

en

Original Abstract

This paper presents the procedure for on-line visual-content-based video synchronization. The motivation of our pioneering work is the existence of several off-line video processing systems employed in video classification or summarization applications, but no evidence of on-line solutions for video analysis. In some applications, the video streams go through the broadcast systems that delay the original video and also distort the original signal. The system that would be able to automatically detect such delays, transmission errors, distortions or broadcast failure is highly required. Our solution employs visual vocabularies that allow signing the video frames by bag-of-words. The synchronization procedure is then based on searching for similar frames from different video streams. This paper also overviews the state-of-the-art techniques required for visual vocabulary building and discuss the convenient properties of techniques for real-time on-line systems.

English abstract

This paper presents the procedure for on-line visual-content-based video synchronization. The motivation of our pioneering work is the existence of several off-line video processing systems employed in video classification or summarization applications, but no evidence of on-line solutions for video analysis. In some applications, the video streams go through the broadcast systems that delay the original video and also distort the original signal. The system that would be able to automatically detect such delays, transmission errors, distortions or broadcast failure is highly required. Our solution employs visual vocabularies that allow signing the video frames by bag-of-words. The synchronization procedure is then based on searching for similar frames from different video streams. This paper also overviews the state-of-the-art techniques required for visual vocabulary building and discuss the convenient properties of techniques for real-time on-line systems.

Keywords

On-line video processing, visual vocabulary, video synchronization

RIV year

2010

Released

01.12.2010

Publisher

University of West Bohemia in Pilsen

Location

Plzeň

ISBN

978-80-86943-88-6

Book

Proceedings of WSCG'10

Edition

18th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2010

Edition number

NEUVEDEN

Pages from

31

Pages to

34

Pages count

7

URL

Documents

BibTex


@inproceedings{BUT34644,
  author="Vítězslav {Beran} and Adam {Herout} and Pavel {Zemčík}",
  title="On-line Video Synchronization Based on Visual Vocabularies",
  annote="This paper presents the procedure for on-line visual-content-based video
synchronization. The motivation of our pioneering work is the existence of
several off-line video processing systems employed in video classification or
summarization applications, but no evidence of on-line solutions for video
analysis. In some applications, the video streams go through the broadcast
systems that delay the original video and also distort the original signal. The
system that would be able to automatically detect such delays, transmission
errors, distortions or broadcast failure is highly required. Our solution employs
visual vocabularies that allow signing the video frames by bag-of-words. The
synchronization procedure is then based on searching for similar frames from
different video streams. This paper also overviews the state-of-the-art
techniques required for visual vocabulary building and discuss the convenient
properties of techniques for real-time on-line systems.",
  address="University of West Bohemia in Pilsen",
  booktitle="Proceedings of WSCG'10",
  chapter="34644",
  edition="18th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2010",
  howpublished="online",
  institution="University of West Bohemia in Pilsen",
  year="2010",
  month="december",
  pages="31--34",
  publisher="University of West Bohemia in Pilsen",
  type="conference paper"
}