DocumentCode
1880108
Title
Sports video classification using HMMS
Author
Gibert, Xavier ; Li, Huiping ; Doermann, David
Author_Institution
Language & Media Process. Lab., Maryland Univ., College Park, MD, USA
Volume
2
fYear
2003
fDate
6-9 July 2003
Abstract
In this paper we address the problem of sports video classification using hidden Markov models (HMMs). For each sports genre, we construct two HMMs representing motion and color features respectively. The observation sequences generated from the principal motion direction and the principal color of each frame are fed to a motion and a color HMM respectively. The outputs are integrated to make a final decision. We tested our scheme on 220 minutes of sports video with four genre types: ice hockey, basketball, football, and soccer, and achieved an overall classification accuracy of 93%.
Keywords
hidden Markov models; image classification; principal component analysis; sport; video signal processing; color features; hidden Markov models; motion features; principal motion direction; sports video classification; Cameras; Educational institutions; Feature extraction; Hidden Markov models; Ice; Laboratories; Principal component analysis; Streaming media; Testing; Transform coding;
fLanguage
English
Publisher
ieee
Conference_Titel
Multimedia and Expo, 2003. ICME '03. Proceedings. 2003 International Conference on
Print_ISBN
0-7803-7965-9
Type
conf
DOI
10.1109/ICME.2003.1221624
Filename
1221624
Link To Document