Abstract
Sensor networks play an increasing role in domains like security surveillance or environmental monitoring. One challenge in such systems is proper adaptation to and interpretation of events in the sensing area of an individual node; another challenge is the integration of observations from individual nodes into a common semantic representation of the environment. We describe a novel hierarchical architecture framework called SENSE (smart embedded network of sensing entities) to meet these challenges. Combining multi-modal sensor information from audio and video modalities to gain relevant information about the sensed environment, each node recognizes a set of predefined behaviors and learns about usual behavior. Neighbor nodes exchange such information to confirm unusual observations and establish a global view. Deviations from “normality” are repor ted in a way understandable for human operators without special training.
This work is partially funded by the European Commission under contract No. 033279 within the Sixth Framework Program for Research and Technological Development.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
www.sense-ist.org (SENSE project website) (accessed April 1, 2009)
Khan, Z., Balch, T., Dellaert, F.: An MCMC-based particle filter for tracking multiple interacting targets. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(12), 1960–1972 (2006)
Bishop, C.M.: Neural networks for pattern recognition. Oxford University Press Inc., New York (1995)
Zucker (né Pratl), G., Frangu, L.: Smart nodes for semantic analysis of visual and aural data. In: Proc. IEEE Conference INDIN, pp. 1001–1006 (2007)
Sallans, B., Bruckner, D., Russ, G.: Statistical detection of alarm conditions in building automation systems. In: Proc. IEEE Conference INDIN, pp. 6–9 (2006)
Crick, C., Pfeffer, A.: Loopy belief propagation as a basis for communication in sensor networks. In: Proc. UAI Conference on uncertainty in Artificial Intelligence, pp. 159–166 (2003)
Yedidia, J.S., Freeman, W.T., Weiss, Y.: Characterization of belief propagation and its generalizations (2001), http://www.merl.com/publications/TR2001-015/ (accessed April 1, 2009)
Lee, D.S.: On-line adaptive Gaussian mixture learning for video applications. In: Proc. 8th Conference on Computer Vision, Prague, Czech Republic (2004), http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.29.2197 (accessed March 29, 2009)
Vlassis, N., Likas, A.: A greedy EM algorithm for Gaussian mixture learning. Neural Proc. Letters 15(1) (2002), http://www.cs.uoi.gr/~arly/papers/gem-npl.ps.gz (accessed March 30, 2009)
Ghahramani, Z., Beal, M.J.: Variation inference for Bayesian mixtures of factor analyzers. In: Advances in neural information processing systems. MIT Press, Cambridge (2000)
Ueda, N., Nakano, R., Ghahramani, Z., Hinton, G.E.: SMEM algorithm for mixture models. Neural Computation Archive 12 (2002)
Ghahramani, Z., Hinton, G.E.: The EM algorithm for mixture of factor analyzers. Technical Report CRG-TR-96-1, University of Toronto (1996)
Lombardi, P.: Study on data fusion techniques for visual modules. Technical Report, University of Pavia (2002)
Burgstaller, W.: Interpretation of situations in buildings. Dissertation thesis, Vienna University of Technology (2007)
Kindermann, R., Snell, J.L.: Markov random fields and their applications. AMS Books Online, ISBN: 0-8218-3381-2 (1980), www.ams.org/online_bks/conm1 (accessed March 24, 2009)
Bauer, D., Brändle, N., Seer, S., Pflugfelder, R.: Finding highly frequented paths in video sequences. In: Proc. 18th Intern. Conference on Pattern Recognition (ICPR 2006), Hong Kong, China, pp. 387–391 (2006)
Fritzke, B.: A growing neural gas network leans topologies. In: Advances in Neural Information Processing Systems, vol. 7, pp. 625–632 (1995)
Pflugfelder, R.P.: Visual traffic surveillance using real-time tracking. TR PRIP, Vienna University of Technology (2002), http://www.icg.tu-graz.ac.at/pub/pubobjects/pflugfelder2002 (accessed March 25, 2009)
Bruckner, D., Kasbi, J., Velik, R., Herzner, W.: High-level hierarchical semantic processing framework for smart sensor networks. In: Proc. IEEE Conference on Human System Interaction, Cracow, Poland, pp. 668–673 (2008)
Picus, C., Cambrini, L., Herzner, W.: Boltzmann machine learning approach for distributed sensor networks using loopy belief propagation inference. In: Proc. 7th Intern. Conference on Machine Learning and Applications, San Diego, CA, pp. 344–349 (2008)
Wide, P.: The electronic head: a virtual quality instrument. IEEE Transactions on Industrial Electronics (48), 766–769 (2001)
Simo, J., Benet, G., Andreu, G.: Embedded video processing for distributed intelligent sensor networks. In: Proc. 3rd Intern. Conference From Scientific Computing to Computational Engineering, Athens, Greece (2008)
Tsahalis, D., Nokas, G., Tsokas, K., Photeinos, D.: The use of decision tree classifiers for the detection of sound objects using microphone array filtered data. Part I and II. In: Proc. 3rd intern. conference From Scientific Computing to computational Engineering, Athens, Greece (2008)
Yin, G.Q., Bruckner, D., Zucker, G.: Statistical modeling of video object’s behavior for improved object tracking in visual surveillance. In: Proc. IEEE ICIT Conference, Churchill, Victoria, Australia (2009)
Anon. CAVIAR dataset, http://homepages.inf.ed.ac.uk/rbf/CAVIARDATA1/ (accessed March 26, 2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Bruckner, D., Picus, C., Velik, R., Herzner, W., Zucker, G. (2009). High-Level Hierarchical Semantic Processing Framework for Smart Sensor Networks. In: Hippe, Z.S., Kulikowski, J.L. (eds) Human-Computer Systems Interaction. Advances in Intelligent and Soft Computing, vol 60. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03202-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-03202-8_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03201-1
Online ISBN: 978-3-642-03202-8
eBook Packages: EngineeringEngineering (R0)