Deakin University
Browse
chen-astatisticaldriven-2005.pdf (482.96 kB)

A statistical-driven approach for automatic classification of events in AFL video highlights

Download (482.96 kB)
conference contribution
posted on 2005-01-01, 00:00 authored by D Tjondronegoro, Yi-Ping Phoebe Chen, B Pham
Due to the repetitive and lengthy nature, automatic content-based summarization is essential to extract a more compact and interesting representation of sport video. State-of-the art approaches have confirmed that high-level semantic in sport video can be detected based on the occurrences of specific audio and visual features (also known as cinematic). However, most of them still rely heavily on manual investigation to construct the algorithms for highlight detection. Thus, the primary aim of this paper is to demonstrate how the statistics of cinematic features within play-break sequences can be used to less-subjectively construct highlight classification rules. To verify the effectiveness of our algorithms, we will present some experimental results using six AFL (Australian Football League) matches from different broadcasters. At this stage, we have successfully classified each play-break sequence into: goal, behind, mark, tackle, and non-highlight. These events are chosen since they are commonly used for broadcasted AFL highlights. The proposed algorithms have also been tested successfully with soccer video.

History

Event

Australasian Computer Science Conference (28th : 2005 : Newcastle, N.S.W.)

Pagination

209 - 218

Publisher

Australian Computer Society

Location

Newcastle, Australia

Place of publication

Sydney, N.S.W.

Start date

2005-01-01

End date

2005-01-31

ISBN-13

9781920682200

ISBN-10

1920682201

Language

eng

Publication classification

E1 Full written paper - refereed

Copyright notice

2005, Australian Computer Society

Editor/Contributor(s)

V Estivill-Castro

Title of proceedings

Proceedings of the twenty eighth Australasian Computer Science Conference (ACSC 2005) Newcastle, Australia, January, 2005

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC