HMM model selection issues for soccer video
Baillie, M. and Jose, J.M. and van Rijsbergen, C.J.; (2004) HMM model selection issues for soccer video. In: Lecture Notes in Computer Science. Springer. ISBN 0302-9743
Full text not available in this repository.Request a copy from the Strathclyde authorAbstract
There has been a concerted effort from the Video Retrieval community to develop tools that automate the annotation process of Sports video. In this paper, we provide an in-depth investigation into three Hidden Markov Model (HMM) selection approaches. Where HMM, a popular indexing framework, is often applied in a ad hoc manner. We investigate what effect, if any, poor HMM selection can have on future indexing performance when classifying specific audio content. Audio is a rich source of information that can provide an effective alternative to high dimensional visual or motion based features. As a case study, we also illustrate how a superior HMM framework optimised using a Bayesian HMM selection strategy, can both segment and then classify Soccer video, yielding promising results.
Creators(s): | Baillie, M., Jose, J.M. and van Rijsbergen, C.J.; | Item type: | Book Section |
---|---|
ID code: | 2730 |
Keywords: | information retrieval, video retrieval, learning objects, hidden Markov model, classification, sport, Electronic computers. Computer science |
Subjects: | Science > Mathematics > Electronic computers. Computer science |
Department: | Faculty of Science > Computer and Information Sciences |
Depositing user: | Strathprints Administrator |
Date deposited: | 28 Mar 2007 |
Last modified: | 20 Jan 2021 15:10 |
URI: | https://strathprints.strath.ac.uk/id/eprint/2730 |
Export data: |