Abstract | ||
---|---|---|
We describe an online method for selecting and annotating highlight scenes in soccer matches being televised. The stadium crowd noise and the play-by-play announcer's voice are used as input signals. Candidate scenes for highlights are extracted from the crowd noise by dynamic thresholding and spectral envelope analysis. Using a dynamic threshold solves the problem in conventional methods of how to determine an appropriate threshold. Semantic-meaning information about the kind of play and the related team and player is extracted from the announcer's commentary by using domain-based rules. The information extracted from the two types of audio input is integrated to generate segment-metadata of highlight scenes. Application of the method to six professional soccer games has confirmed its effectiveness. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1093/ietisy/e90-1.1.224 | IEICE Transactions |
Keywords | Field | DocType |
conventional method,highlight scenes,audio input,crowd noise,dynamic thresholding,dynamic threshold,appropriate threshold,televised soccer,input signal,semantic-meaning information,annotating highlight scene,highlight scene,automatic real-time selection,real time | Computer vision,Metadata,Annotation,Spectral envelope,Stadium,Computer science,Speech recognition,Artificial intelligence,Thresholding | Journal |
Volume | Issue | ISSN |
E90-D | 1 | 1745-1361 |
Citations | PageRank | References |
3 | 0.47 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Masanori Sano | 1 | 39 | 8.04 |
Ichiro Yamada | 2 | 87 | 17.38 |
Hideki Sumiyoshi | 3 | 43 | 9.08 |
Nobuyuki Yagi | 4 | 65 | 14.03 |