CONF Korchagin_AC_2009/IDIAP Out-of-Scene AV Data Detection Korchagin, Danil confidence estimation pattern matching time-frequency analysis EXTERNAL https://publications.idiap.ch/attachments/papers/2009/Korchagin_AC_2009.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Korchagin_Idiap-RR-31-2009 Related documents Proceedings IADIS International Conference Applied Computing Rome, Italy 2 244-248 978-972-8924-97-3 2009 P.O. Box 592, CH-1920 Martigny, Switzerland November 2009 In this paper, we propose a new approach for the automatic audio-based out-of-scene detection of audio-visual data, recorded by different cameras, camcorders or mobile phones during social events. All recorded data is clustered to out-of-scene and in-scene datasets based on confidence estimation of cepstral pattern matching with a common master track of the event, recorded by a reference camera. The core of the algorithm is based on perceptual time-frequency analysis and confidence measure based on distance distribution variance. The results show correct clustering in 100% of cases for a real life dataset and surpass the performance of cross correlation while keeping lower system requirements. REPORT Korchagin_Idiap-RR-31-2009/IDIAP Out-of-Scene AV Data Detection Korchagin, Danil confidence estimation pattern matching time-frequency analysis EXTERNAL https://publications.idiap.ch/attachments/reports/2009/Korchagin_Idiap-RR-31-2009.pdf PUBLIC Idiap-RR-31-2009 2009 Idiap P.O. Box 592, CH-1920 Martigny, Switzerland November 2009 In this paper, we propose a new approach for the automatic audio-based out-of-scene detection of audio-visual data, recorded by different cameras, camcorders or mobile phones during social events. All recorded data is clustered to out-of-scene and in-scene datasets based on confidence estimation of cepstral pattern matching with a common master track of the event, recorded by a reference camera. The core of the algorithm is based on perceptual time-frequency analysis and confidence measure based on distance distribution variance. The results show correct clustering in 100% of cases for a real life dataset and surpass the performance of cross correlation while keeping lower system requirements.