Abstract
This chapter provides modern view on the super-extended objects monitoring . The monitoring process is being reduced to the detection and classification of targeted events occurred in the vicinity of the controlled object by tracking changes in the internal state of the monitored object and by search for precursors of an environmental change, which can serve as precursors to natural and technological disasters. Suggested approach is based on the multimodal concept of the monitoring object observation, heterogeneous data fusion, detection and classification of targeted events. The approach assumes that different types of physical field are observed simultaneously in real time, data is received from different types of sensors in various rate with different accuracy, with insufficient prior information about distribution probability of targeted signals and background noises. The suggested approach provides stable detection of targeted events, which guarantees upper bounds for probabilities of type I and type II errors. Identification of targeted events type (classification problem) is based on the heterogeneous data fusion methodology. The application results of the proposed approach in the real monitoring system are presented herein.
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
References
Choi, K.N., Juarez, J.C., Taylor, H.F.: Distributed fiber optic pressure/seismic sensor for low-cost monitoring of long perimeters. In: Proceedings of SPIE 5090, Unattended Ground Sensor Technologies and Applications, pp. 134–141 (2003)
Korotaev, V., Denisov, V.M., Timofeev, A.V., Serikova, M.V.: Analysis of seismoacoustic activity based on using optical fiber classifier. In: Latin America Optics and Photonics Conference, OSA Technical Digest (online) (Optical Society of America, 2014), paper LM4A.22 (2014)
Hampel, F.R, Ronchetti, E.M., Rousseeuw, P.J., Stahel, W.A.: Robust Statistics. The Approach Based on Influence Functions. Wiley, New York
Harrison, D.K., Hawthorn, I.E.: Amputation level viability in critical limb ischaemia: Setting new standards. Adv. Exp. Med. Biol. 566, 325–332 (2005)
Huber, P.: Robust Statistics. Wiley, New York (1981)
Maronna, R., Yohai, D.M.: Robust Statistics. Theory and Methods. Wiley, New York (2006)
Shevlyakov, R., Smirnov, R.: Robust estimation of the correlation coefficient: an attempt of survey. Austrian J. Stat. 40(1 & 2), 147–156 (2011)
Mei, Y.: Sequential change-point detection when unknown parameters are present in the pre-change distribution. Ann. Stat. 34, 92–122 (2006)
Lai, T.L.: Sequential Change point detection in quality control and dynamical systems. J. R. Stat. Soc. Ser. B 57, 613–658 (1995)
Elhoseiny, M., Bakry, A., Elgammal, A.: Multiclass object classification in video surveillance systems—experimental study. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW’13), pp. 788–793. IEEE Computer Society, Washington, DC, USA (2013)
Lowe, D.G.: Distinctive image features from scale-invariant key-points. IJCV 60(2), 91–110 (2014)
Tan, M., Wang, L., Tsang, I.W.: Learning sparse svm for feature selection on very high dimensional datasets. ICML 1047–1054 (2010)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 1, pp. 886–893 (2005)
Laptev, I.: On space-time interest points. IJCV 64(2–3), 107–123 (2005)
Wang, I., Klaser, A., Schmid, C.: Dense trajectories and motion boundary descriptors for action recognition. IJCV 103(1), 60–79 (2013)
Timofeev, A.V., Egorov, D.V.: Bimodal System for Surveillance of Super-extended Objects. Vol. 1, pp. 57–62. IWSSS-2014, At Bucharest (2014)
Gehler, V., Nowozin, S.: On feature combination for multiclass object classification. Int. Conf. Comput. Vision, IEEE 221–228 (2009)
Ratsch, G., Scholkopf, B., Smola, A.: Robust ensemble learning. In: Smola A.J, Bartlett P.L., Scholkopf B., Schuurmans D. (eds.) Advances in Large Margin Classifiers, pp. 208–222. MIT Press (1999)
Hears, M., Dumais, S., Platt, J., Scholkopf, B.: Support vector machines. IEEE Intell. Syst. 13(4), 18–28 (1998)
Timofeev, A.V.: The guaranteed estimation of the Lipschitz classifier accuracy: confidence set approach. J. Korean Stat. Soc. 41(1), 105–114 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Timofeev, A.V., Denisov, V.M. (2016). Multimodal Heterogeneous Monitoring of Super-Extended Objects: Modern View. In: Pricop, E., Stamatescu, G. (eds) Recent Advances in Systems Safety and Security. Studies in Systems, Decision and Control, vol 62. Springer, Cham. https://doi.org/10.1007/978-3-319-32525-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-32525-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-32523-1
Online ISBN: 978-3-319-32525-5
eBook Packages: EngineeringEngineering (R0)