Presentation 2004/11/12
Automatic video indexing of baseball broadcast using a hidden Markov model
Nguyen HUU BACH, Koichi SHINODA, Sadaoki FURUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a statistical framework for in indexing the content of baseball broadcast video, with the object of extracting highlight scenes. It employs a Hidden Markov Model (HMM) with multi-streams in which the weights of the following three different feature types are controlled: principle component features, fractal features, and difference features. It also utilizes camera-shot recognition for scene boundary detection. Experimental results for 4.5 hours of digest data demonstrate the effectiveness of the proposed framework. The recognition rate for 8 scenes was 76.8%, which was 11.6 points better than that obtained with a single-stream HMM having no boundary detection.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) HMM / video indexing / difference feature / fractal feature / scene detection
Paper # PRMU2004-107,HIP2004-47
Date of Issue

Conference Information
Committee HIP
Conference Date 2004/11/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic video indexing of baseball broadcast using a hidden Markov model
Sub Title (in English)
Keyword(1) HMM
Keyword(2) video indexing
Keyword(3) difference feature
Keyword(4) fractal feature
Keyword(5) scene detection
1st Author's Name Nguyen HUU BACH
1st Author's Affiliation Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology()
2nd Author's Name Koichi SHINODA
2nd Author's Affiliation Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
3rd Author's Name Sadaoki FURUI
3rd Author's Affiliation Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
Date 2004/11/12
Paper # PRMU2004-107,HIP2004-47
Volume (vol) vol.104
Number (no) 450
Page pp.pp.-
#Pages 6
Date of Issue