Analysis of Time-multiplexed Security Videos

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.

[1]  Ákos Utasi,et al.  HMM-based unusual motion detection without tracking , 2008, 2008 19th International Conference on Pattern Recognition.

[2]  Leah H. Jamieson,et al.  Modeling duration in a hidden Markov model with the exponential family , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  N. Nikolaidis,et al.  Video shot detection and condensed representation. a review , 2006, IEEE Signal Processing Magazine.

[4]  Yuchou Chang,et al.  Unsupervised Video Shot Detection Using Clustering Ensemble with a Color Global Scale-Invariant Feature Transform Descriptor , 2008, EURASIP J. Image Video Process..

[5]  H. Kobayashi,et al.  An efficient forward-backward algorithm for an explicit-duration hidden Markov model , 2003, IEEE Signal Processing Letters.

[6]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for automatic speech recognition , 1986 .

[7]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[8]  R. Moore,et al.  Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  W. Eric L. Grimson,et al.  Learning Patterns of Activity Using Real-Time Tracking , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Ahmed H. Tewfik,et al.  Eigen-image based video segmentation and indexing , 1997, Proceedings of International Conference on Image Processing.

[11]  István Petrás,et al.  Flexible test-bed for unusual behavior detection , 2007, CIVR '07.

[12]  M. T. Johnson,et al.  Capacity and complexity of HMM duration modeling techniques , 2005, IEEE Signal Processing Letters.

[13]  Huadong Ma,et al.  A Hidden Markov Model Approach to Parsing MTV Video Shot , 2008, 2008 Congress on Image and Signal Processing.

[14]  Tamás Szirányi,et al.  Bayesian Foreground and Shadow Detection in Uncertain Frame Rate Surveillance Videos , 2008, IEEE Transactions on Image Processing.