TennisSense: A platform for extracting semantic information from multi-camera tennis data

作者: Ciaran O Conaire , Philip Kelly , Damien Connaghan , Noel E. O'Connor

DOI: 10.1109/ICDSP.2009.5201152

关键词: Object detectionFeature extractionImage retrievalMotion detectionTennis ballSearch engine indexingComputer visionComputer scienceBackground subtractionArtificial intelligenceMetadata

摘要: In this paper, we introduce TennisSense, a technology platform for the digital capture, analysis and retrieval of tennis training matches. Our algorithms extracting useful metadata from overhead court camera are described evaluated. We track ball using motion images candidate detection then link candidates into locally linear tracks. From these tracks can infer when serves rallies take place. Using background subtraction hysteresis-type blob tracking, players positions. The performance both modules is evaluated ground-truthed data. extracted provides valuable information indexing efficient browsing hours multi-camera footage briefly illustrative how data used by our tennis-coach playback interface.

参考文章(10)
Douglas Brent West, Introduction to Graph Theory ,(1995)
H. Miyamori, S.-I. Iisaku, Video annotation for content-based retrieval using human behavior analysis and domain knowledge ieee international conference on automatic face and gesture recognition. pp. 320- 325 ,(2000) , 10.1109/AFGR.2000.840653
Jessica K. Hodgins, Ronit Slyper, Action capture with accelerometers symposium on computer animation. pp. 193- 199 ,(2008) , 10.5555/1632592.1632620
F. Yan, W. Christmas, J. Kittler, A Tennis Ball Tracking Algorithm for Automatic Annotation of Tennis Match british machine vision conference. ,(2005) , 10.5244/C.19.67
C. Stauffer, W.E.L. Grimson, Adaptive background mixture models for real-time tracking computer vision and pattern recognition. ,vol. 2, pp. 246- 252 ,(1999) , 10.1109/CVPR.1999.784637
Giuseppe Torre, Mikael Fernström, Brendan O'Flynn, Philip Angove, Celeritas: wearable wireless system new interfaces for musical expression. pp. 205- 208 ,(2007) , 10.1145/1279740.1279780
G.S. Pingali, Y. Jean, I. Carlbom, Real time tracking for enhanced tennis broadcasts computer vision and pattern recognition. pp. 260- 265 ,(1998) , 10.1109/CVPR.1998.698618
D.A. Sadlier, N.E. O'Connor, Event detection in field sports video using audio-visual features and a support vector Machine IEEE Transactions on Circuits and Systems for Video Technology. ,vol. 15, pp. 1225- 1233 ,(2005) , 10.1109/TCSVT.2005.854237
G. Pingali, A. Opalach, Y. Jean, Ball tracking and virtual replays for innovative tennis broadcasts Proceedings 15th International Conference on Pattern Recognition. ICPR-2000. ,vol. 4, pp. 4152- 4156 ,(2000) , 10.1109/ICPR.2000.902885
P. Viola, M. Jones, Rapid object detection using a boosted cascade of simple features computer vision and pattern recognition. ,vol. 1, pp. 511- 518 ,(2001) , 10.1109/CVPR.2001.990517