Detecting irregular camera events in time-multiplexed videos
Ákos Utasi, László Czúni · Electronics Letters · 2009
Novel robust statistical methods for detecting irregular camera events in time-multiplexed video streams are presented. Hidden Markov and hidden semi-Markov model based real-time detectors have been developed for video segmentation and anomalous event detection. The performance of the detectors has been demonstrated with real-life outdoor videos recorded by low-quality cameras.