Robust Scene Extraction Using Multi-Stream HMMs for Baseball Broadcast

Nguyen Huu BACH
Koichi SHINODA
Sadaoki FURUI

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E89-D    No.9    pp.2553-2561
Publication Date: 2006/09/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e89-d.9.2553
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Processing and Video Processing
Keyword: 
CBVIR,  HMM,  scene extraction,  game adaptation,  

Full Text: PDF(1MB)>>
Buy this Article


Summary: 
In this paper, we propose a robust statistical framework for extracting scenes from a baseball broadcast video. We apply multi-stream hidden Markov models (HMMs) to control the weights among different features. To achieve a large robustness against new scenes, we used a common simple structure for all the HMMs. In addition, scene segmentation and unsupervised adaptation were applied to achieve greater robustness against differences in environmental conditions among games. The F-measure of scene-extracting experiments for eight types of scene from 4.5 hours of digest data was 77.4% and was increased to 78.7% by applying scene segmentation. Furthermore, the unsupervised adaptation method improved precision by 2.7 points to 81.4%. These results confirm the effectiveness of our framework.

open access publishing via