Analysis of Time-multiplexed Security Videos
Ákos Utasi, László Czúni · 2009
In this paper we present robust statistical methods for segmentation and preprocessing of time-multiplexed videos. We will present hidden Markov and hidden semi-Markov model based real-time detectors and their usage for video segmentation and anomalous event detection. We demonstrate the high performance of our detectors with real-life outdoor videos from low-quality cameras.