Abstract | ||
---|---|---|
this paper presents a novel method for highlight extraction in sports video, which fuses multi-modal features including audio and visual. At first, we detect slow-motion replay based on logo, and then detect audience cheers based on pitch frequency and short-time energy. In the next step, we fuse audio-visual features to detect highlight events through using a special “and” ( ) operation. The method is general to most genres of sports game because the audience cheers and slow-motion replay are a reliable clue to the highlight and the features we utilize is not limited in a specific kind of sports game. Experimental results show that the approach is valid and avoid the deficiency of detecting highlight events by a single feature. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/MUE.2009.25 | MUE |
Keywords | Field | DocType |
highlight extraction,slow-motion replay,unified sports video highlight,novel method,multi-modal feature,audience cheer,highlight event,fuse audio-visual feature,sports video,multi-feature fusion,sports game,motion estimation,data mining,visualization,feature extraction,image fusion,videoconference,noise,sport,fuses,color,pervasive computing,histograms,frequency,games | Computer vision,Feature fusion,Image fusion,Pitch Frequency,Computer science,Visualization,Logo,Feature extraction,Artificial intelligence,Motion estimation,Fuse (electrical) | Conference |
Citations | PageRank | References |
3 | 0.42 | 8 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu Song | 1 | 356 | 52.74 |
Wenhong Wang | 2 | 3 | 0.42 |