Event detection and summarization in American football broadcast video

Baoxin Li, Ibrahim Sezan

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

52 Citations (Scopus)

Abstract

We propose a framework for event detection and summary generation in football broadcast video. First, we formulate summarization as a play detection problem, with play being defined as the most basic segment of time during which the ball is being played. Then we propose both deterministic and probabilistic approaches to the detection of the plays. The detected plays are concatenated to generate a compact, time-compressed summary of the original video. Such a summary is complete in the sense that it contains every meaningful action of the underlying game, and it also servers as a much better starting point for higher-level summarization and other analyses than the original video does. Based on the summary, we also propose an audio-based hierarchical summarization method. Experimental results show the proposed methods work very well on consumer grade platforms.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsM.M. Yeung, C.S. Li, R.W. Lienhart
Pages202-213
Number of pages12
Volume4676
DOIs
StatePublished - 2002
Externally publishedYes
EventStorage and Retrieval for Media Databases 2002 - San Jose, CA, United States
Duration: Jan 23 2002Jan 25 2002

Other

OtherStorage and Retrieval for Media Databases 2002
CountryUnited States
CitySan Jose, CA
Period1/23/021/25/02

Fingerprint

Servers
games
balls
grade
platforms

Keywords

  • Event detection
  • Video summarization

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Li, B., & Sezan, I. (2002). Event detection and summarization in American football broadcast video. In M. M. Yeung, C. S. Li, & R. W. Lienhart (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 4676, pp. 202-213) https://doi.org/10.1117/12.451092

Event detection and summarization in American football broadcast video. / Li, Baoxin; Sezan, Ibrahim.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / M.M. Yeung; C.S. Li; R.W. Lienhart. Vol. 4676 2002. p. 202-213.

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

Li, B & Sezan, I 2002, Event detection and summarization in American football broadcast video. in MM Yeung, CS Li & RW Lienhart (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 4676, pp. 202-213, Storage and Retrieval for Media Databases 2002, San Jose, CA, United States, 1/23/02. https://doi.org/10.1117/12.451092
Li B, Sezan I. Event detection and summarization in American football broadcast video. In Yeung MM, Li CS, Lienhart RW, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 4676. 2002. p. 202-213 https://doi.org/10.1117/12.451092
Li, Baoxin ; Sezan, Ibrahim. / Event detection and summarization in American football broadcast video. Proceedings of SPIE - The International Society for Optical Engineering. editor / M.M. Yeung ; C.S. Li ; R.W. Lienhart. Vol. 4676 2002. pp. 202-213
@inproceedings{680175de3c734baeb4b2765db310a532,
title = "Event detection and summarization in American football broadcast video",
abstract = "We propose a framework for event detection and summary generation in football broadcast video. First, we formulate summarization as a play detection problem, with play being defined as the most basic segment of time during which the ball is being played. Then we propose both deterministic and probabilistic approaches to the detection of the plays. The detected plays are concatenated to generate a compact, time-compressed summary of the original video. Such a summary is complete in the sense that it contains every meaningful action of the underlying game, and it also servers as a much better starting point for higher-level summarization and other analyses than the original video does. Based on the summary, we also propose an audio-based hierarchical summarization method. Experimental results show the proposed methods work very well on consumer grade platforms.",
keywords = "Event detection, Video summarization",
author = "Baoxin Li and Ibrahim Sezan",
year = "2002",
doi = "10.1117/12.451092",
language = "English (US)",
volume = "4676",
pages = "202--213",
editor = "M.M. Yeung and C.S. Li and R.W. Lienhart",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Event detection and summarization in American football broadcast video

AU - Li, Baoxin

AU - Sezan, Ibrahim

PY - 2002

Y1 - 2002

N2 - We propose a framework for event detection and summary generation in football broadcast video. First, we formulate summarization as a play detection problem, with play being defined as the most basic segment of time during which the ball is being played. Then we propose both deterministic and probabilistic approaches to the detection of the plays. The detected plays are concatenated to generate a compact, time-compressed summary of the original video. Such a summary is complete in the sense that it contains every meaningful action of the underlying game, and it also servers as a much better starting point for higher-level summarization and other analyses than the original video does. Based on the summary, we also propose an audio-based hierarchical summarization method. Experimental results show the proposed methods work very well on consumer grade platforms.

AB - We propose a framework for event detection and summary generation in football broadcast video. First, we formulate summarization as a play detection problem, with play being defined as the most basic segment of time during which the ball is being played. Then we propose both deterministic and probabilistic approaches to the detection of the plays. The detected plays are concatenated to generate a compact, time-compressed summary of the original video. Such a summary is complete in the sense that it contains every meaningful action of the underlying game, and it also servers as a much better starting point for higher-level summarization and other analyses than the original video does. Based on the summary, we also propose an audio-based hierarchical summarization method. Experimental results show the proposed methods work very well on consumer grade platforms.

KW - Event detection

KW - Video summarization

UR - http://www.scopus.com/inward/record.url?scp=0036031237&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036031237&partnerID=8YFLogxK

U2 - 10.1117/12.451092

DO - 10.1117/12.451092

M3 - Conference contribution

VL - 4676

SP - 202

EP - 213

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

A2 - Yeung, M.M.

A2 - Li, C.S.

A2 - Lienhart, R.W.

ER -