Automatic pitching scene archiving system for video indexing support

Yuki Shono, Yoshimitsu Aoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A content-based scene indexing has been important technique for an effective video contents handling such as scene retrieval and editing. The standard multimedia content descriptor (MPEG7) has been proposed for the key scene indexing. As for an automatic scene indexing, audio-visual features are most important clues. Many methods have been proposed for effective scene indexing based on those features, in this paper, we propose an automatic key scene detection method for baseball video contents using video features. We regard pitching scenes as key scenes, because they are starting points of all baseball play scenes. If the pitching scenes are detected, they could be effective hints to detect other scenes. In addition, a pitching scene digest video can be easily edited by gathering automatically extracted scenes. The pitching scene digest can be useful data for pitching analysis. We extract pitching scenes using color, domain and motion template created from manually selected pitching scene samples. Those templates contain image features unique to pitching scenes. Template matching is applied to video stream, so that target scenes can be detected by judging calculated matching rate. We experimentally test our method for actual baseball video contents. It can be useful data for pitching analysis and editing of digest news broad casting. We are developing the video indexing support system which users can give text annotations to indexed scenes using MPEG7 format descriptors.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsS. Kaneko, H. Cho, G.K. Knopf, R. Tutsch
Pages199-207
Number of pages9
Volume5603
DOIs
Publication statusPublished - 2004
Externally publishedYes
EventMachine Vision and its Optomechatronic Applications - Philadelphia, PA, United States
Duration: 2004 Oct 262004 Oct 28

Other

OtherMachine Vision and its Optomechatronic Applications
CountryUnited States
CityPhiladelphia, PA
Period04/10/2604/10/28

Fingerprint

Automatic indexing
Template matching
Casting
Color
editing
templates
annotations
support systems
news
multimedia
format
retrieval
color

Keywords

  • Motion Picture Analysis
  • MPEG7
  • Scene Detection
  • Video Indexing
  • Video Summarization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Shono, Y., & Aoki, Y. (2004). Automatic pitching scene archiving system for video indexing support. In S. Kaneko, H. Cho, G. K. Knopf, & R. Tutsch (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5603, pp. 199-207). [25] https://doi.org/10.1117/12.571037

Automatic pitching scene archiving system for video indexing support. / Shono, Yuki; Aoki, Yoshimitsu.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / S. Kaneko; H. Cho; G.K. Knopf; R. Tutsch. Vol. 5603 2004. p. 199-207 25.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shono, Y & Aoki, Y 2004, Automatic pitching scene archiving system for video indexing support. in S Kaneko, H Cho, GK Knopf & R Tutsch (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5603, 25, pp. 199-207, Machine Vision and its Optomechatronic Applications, Philadelphia, PA, United States, 04/10/26. https://doi.org/10.1117/12.571037
Shono Y, Aoki Y. Automatic pitching scene archiving system for video indexing support. In Kaneko S, Cho H, Knopf GK, Tutsch R, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5603. 2004. p. 199-207. 25 https://doi.org/10.1117/12.571037
Shono, Yuki ; Aoki, Yoshimitsu. / Automatic pitching scene archiving system for video indexing support. Proceedings of SPIE - The International Society for Optical Engineering. editor / S. Kaneko ; H. Cho ; G.K. Knopf ; R. Tutsch. Vol. 5603 2004. pp. 199-207
@inproceedings{e4e8c890ed454a70bbe0d5feef817f6f,
title = "Automatic pitching scene archiving system for video indexing support",
abstract = "A content-based scene indexing has been important technique for an effective video contents handling such as scene retrieval and editing. The standard multimedia content descriptor (MPEG7) has been proposed for the key scene indexing. As for an automatic scene indexing, audio-visual features are most important clues. Many methods have been proposed for effective scene indexing based on those features, in this paper, we propose an automatic key scene detection method for baseball video contents using video features. We regard pitching scenes as key scenes, because they are starting points of all baseball play scenes. If the pitching scenes are detected, they could be effective hints to detect other scenes. In addition, a pitching scene digest video can be easily edited by gathering automatically extracted scenes. The pitching scene digest can be useful data for pitching analysis. We extract pitching scenes using color, domain and motion template created from manually selected pitching scene samples. Those templates contain image features unique to pitching scenes. Template matching is applied to video stream, so that target scenes can be detected by judging calculated matching rate. We experimentally test our method for actual baseball video contents. It can be useful data for pitching analysis and editing of digest news broad casting. We are developing the video indexing support system which users can give text annotations to indexed scenes using MPEG7 format descriptors.",
keywords = "Motion Picture Analysis, MPEG7, Scene Detection, Video Indexing, Video Summarization",
author = "Yuki Shono and Yoshimitsu Aoki",
year = "2004",
doi = "10.1117/12.571037",
language = "English",
volume = "5603",
pages = "199--207",
editor = "S. Kaneko and H. Cho and G.K. Knopf and R. Tutsch",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Automatic pitching scene archiving system for video indexing support

AU - Shono, Yuki

AU - Aoki, Yoshimitsu

PY - 2004

Y1 - 2004

N2 - A content-based scene indexing has been important technique for an effective video contents handling such as scene retrieval and editing. The standard multimedia content descriptor (MPEG7) has been proposed for the key scene indexing. As for an automatic scene indexing, audio-visual features are most important clues. Many methods have been proposed for effective scene indexing based on those features, in this paper, we propose an automatic key scene detection method for baseball video contents using video features. We regard pitching scenes as key scenes, because they are starting points of all baseball play scenes. If the pitching scenes are detected, they could be effective hints to detect other scenes. In addition, a pitching scene digest video can be easily edited by gathering automatically extracted scenes. The pitching scene digest can be useful data for pitching analysis. We extract pitching scenes using color, domain and motion template created from manually selected pitching scene samples. Those templates contain image features unique to pitching scenes. Template matching is applied to video stream, so that target scenes can be detected by judging calculated matching rate. We experimentally test our method for actual baseball video contents. It can be useful data for pitching analysis and editing of digest news broad casting. We are developing the video indexing support system which users can give text annotations to indexed scenes using MPEG7 format descriptors.

AB - A content-based scene indexing has been important technique for an effective video contents handling such as scene retrieval and editing. The standard multimedia content descriptor (MPEG7) has been proposed for the key scene indexing. As for an automatic scene indexing, audio-visual features are most important clues. Many methods have been proposed for effective scene indexing based on those features, in this paper, we propose an automatic key scene detection method for baseball video contents using video features. We regard pitching scenes as key scenes, because they are starting points of all baseball play scenes. If the pitching scenes are detected, they could be effective hints to detect other scenes. In addition, a pitching scene digest video can be easily edited by gathering automatically extracted scenes. The pitching scene digest can be useful data for pitching analysis. We extract pitching scenes using color, domain and motion template created from manually selected pitching scene samples. Those templates contain image features unique to pitching scenes. Template matching is applied to video stream, so that target scenes can be detected by judging calculated matching rate. We experimentally test our method for actual baseball video contents. It can be useful data for pitching analysis and editing of digest news broad casting. We are developing the video indexing support system which users can give text annotations to indexed scenes using MPEG7 format descriptors.

KW - Motion Picture Analysis

KW - MPEG7

KW - Scene Detection

KW - Video Indexing

KW - Video Summarization

UR - http://www.scopus.com/inward/record.url?scp=17644402090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17644402090&partnerID=8YFLogxK

U2 - 10.1117/12.571037

DO - 10.1117/12.571037

M3 - Conference contribution

AN - SCOPUS:17644402090

VL - 5603

SP - 199

EP - 207

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Kaneko, S.

A2 - Cho, H.

A2 - Knopf, G.K.

A2 - Tutsch, R.

ER -