Highlights extraction from sports video based on an audio-visual marker detection framework

Author

Xiong, Ziyou ; Radhakrishnan, Regunathan ; Divakaran, Ajay ; Huang, Thomas S.

Author_Institution

Dept. of Electr. & Comput. Eng., Illinois Univ., Champaign, IL, USA

fYear

2005

fDate

6-8 July 2005

Abstract

We propose to use a visual object (e.g., the baseball catcher) detection algorithm to find local, semantic objects in video frames in addition to an audio classification algorithm to find semantic audio objects in the audio track for sports highlights extraction. The highlight candidates are then further grouped into finer-resolution highlight segments, using color or motion information. During the grouping phase, many of the false alarms can be correctly identified and eliminated. Our experimental results with baseball, soccer and golf video are promising.

Keywords

audio-visual systems; feature extraction; image classification; image colour analysis; image motion analysis; image resolution; image segmentation; object detection; audio classification algorithm; audio-visual marker; baseball; color information; finer-resolution highlight segment; golf video; grouping phase; motion information; semantic object; soccer; sports highlights extraction; visual object detection algorithm; Classification algorithms; Data mining; Detection algorithms; Electronic mail; Feature extraction; Hidden Markov models; Laboratories; Object detection; Speech; Weather forecasting; Audio-Visual Markers; Finer-Resolution Highlights; Sports Highlights;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2005. ICME 2005. IEEE International Conference on

Print_ISBN

0-7803-9331-7

Type

conf

DOI

10.1109/ICME.2005.1521352

Filename

1521352