Out-of-scene AV data detection

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-ofscene 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. KEYWORDS Time-frequency analysis, pattern matching, confidence estimation.

• Type: Journal
• Year: 2009
• Where: IADIS
• Authors: Danil Korchagin
• Keywords: Audio-based Out-of-scene Detection, Confidence Estimation, IADIS 2009, Internet Technology, Time-frequency Analysis