Title :
Detecting irregular camera events in time-multiplexed videos
Author :
Utasi, A. ; Czuni, Laszlo
Author_Institution :
Comput. & Autom. Res. Inst., Hungarian Acad. of Sci., Budapest, Hungary
Abstract :
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.
Keywords :
hidden Markov models; image segmentation; statistical analysis; video cameras; video signal processing; video streaming; anomalous event detection; hidden Markov model; hidden semiMarkov model; irregular camera event detection; real-time detector; robust statistical method; time-multiplexed video streams; video segmentation;
Journal_Title :
Electronics Letters
DOI :
10.1049/el.2009.1000
