High-level hierarchical semantic processing framework for smart sensor networks

This paper presents the framework of a novel approach to combine multi-modal sensor information from audio and video modalities to gain valuable supplementary information compared to traditional video-based observation systems or even just CCTV systems. A hierarchical, multi-modal sensor processing architecture for observation and surveillance systems is proposed. It recognizes a set of pre-defined behavior and learns about usual behavior. Deviations from ldquonormalityrdquo are reported in a way understandable even for staff without special training. The processing architecture including the physical sensor nodes is called SENSE (smart embedded network of sensing entities) (Zucker and Frangu, 2007).

[1]  Geoffrey E. Hinton,et al.  SMEM Algorithm for Mixture Models , 1998, Neural Computation.

[2]  Wolfgang Herzner,et al.  Boltzmann Machine Topology Learning for Distributed Sensor Networks Using Loopy Belief Propagation Inference , 2008, 2008 Seventh International Conference on Machine Learning and Applications.

[3]  W.T. Penzhorn,et al.  Perceptive awareness in building automation , 2005, IEEE 3rd International Conference on Computational Cybernetics, 2005. ICCC 2005..

[4]  Dar-Shyang Lee,et al.  Online Adaptive Gaussian Mixture Learning for Video Applications , 2004, ECCV Workshop SMVP.

[5]  B Fritzke,et al.  A growing neural gas network learns topologies. G. Tesauro, DS Touretzky, and TK Leen, editors , 1995, NIPS 1995.

[6]  D. Bruckner,et al.  Statistical Detection of Alarm Conditions in Building Automation Systems , 2006, 2006 4th IEEE International Conference on Industrial Informatics.

[7]  Lab Visione Artificiale.  A study on data fusion techniques for visual modules , 2002 .

[8]  Dietmar Bauer,et al.  Finding Highly Frequented Paths in Video Sequences , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[9]  Avi Pfeffer,et al.  Loopy Belief Propagation as a Basis for Communication in Sensor Networks , 2002, UAI.

[10]  Samir Kouro,et al.  Unidimensional Modulation Technique for Cascaded Multilevel Converters , 2009, IEEE Transactions on Industrial Electronics.

[11]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[12]  Zoubin Ghahramani,et al.  Variational Inference for Bayesian Mixtures of Factor Analysers , 1999, NIPS.

[13]  Frank Dellaert,et al.  An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets , 2004, ECCV.

[14]  J. Laurie Snell,et al.  Markov Random Fields and Their Applications , 1980 .

[15]  William T. Freeman,et al.  Understanding belief propagation and its generalizations , 2003 .

[16]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[17]  Peter Wide.  The electronic head: a virtual quality instrument , 2001, IEEE Trans. Ind. Electron..

[18]  Dietmar Bruckner,et al.  Statistical modeling of video object's behavior for improved object tracking in visual surveillance , 2009, AFRICON 2009.

[19]  Nikos A. Vlassis,et al.  A Greedy EM Algorithm for Gaussian Mixture Learning , 2002, Neural Processing Letters.

[20]  G. Pratl,et al.  Smart Nodes for Semantic Analysis of Visual and Aural Data , 2007, 2007 5th IEEE International Conference on Industrial Informatics.

[21]  Frank Dellaert,et al.  MCMC Data Association and Sparse Factorization Updating for Real Time Multitarget Tracking with Merged and Multiple Measurements , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.