MOSAIC: A Multi-modal Surveillance System to Enhance Situation Awareness and Decision Making

  • Richard Adderley
  • Atta Badii
  • Rubén Heras Evangelio
  • Matteo Raffaelli
  • Patrick Seidler
  • Marco Tiemann
Part of the Communications in Computer and Information Science book series (CCIS, volume 434)

Abstract

With increasing complexity of systems under surveillance, demand grows for automated video-based surveillance systems which are able to support end users in making sense of situational context from the amount of available data and incoming data streams. Traditionally, those systems have been developed based on techniques derived from the fields of image processing and pattern recognition. This paper presents MOSAIC (Multi-Modal Situation Assessment and Analytics Platform), a system which aims at exploiting multi-modal data analysis comprising advanced tools for video analytics, text mining, social network analysis, and decision support in order to provide from a richer context an understanding of behaviour of the system under surveillance and to support police personnel in decision making processes.

Keywords

Multi-modal data mining social and criminal network analysis video analytics semantic interoperability decision support system 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Horrocks, I.: From SHIQ and RDF to OWL: the making of a web ontology language. Web Semantics: Science Services, and Agents on the World Wide Web 1 (2003)Google Scholar
  2. 2.
    Perez, J., Arenas, M., Gutierrez, C.: Semantics and complexity of SPARQL. ACM Transactions on Database Systems 34(3) (2009)Google Scholar
  3. 3.
    Adderley, R.: Exploring the Differences Between the Cross Industry Process for Data Mining and the National Intelligence Model Using a Self Organising Map Case study. In: Business Intelligence and Performance Management, pp. 91–105. Springer (2013)Google Scholar
  4. 4.
    Shearer, C.: The CRISP-DM model: the new blueprint for data mining. Journal of Data Warehousing 5, 13–22 (2000)Google Scholar
  5. 5.
    Seidler, P., Adderley, R.: Criminal network analysis inside law enforcement agencies – a data mining system approach under the National Intelligence Model. International Journal of Police Science & Management 15(4), 323–337 (2013)CrossRefGoogle Scholar
  6. 6.
    Evangelio, R.H., Paetzold, M., Keller, I., Sikora, T.: Adaptively Splitted GMM with Feedback Improvement for the Task of Background Subtraction. Accepted for Publication in: IEEE Transactions on Information Forensics and Security (2014)Google Scholar
  7. 7.
    Senst, T., Geistert, J., Keller, I., Sikora, T.: Robust Local Optical Flow Estimation using Bilinear Equations for Sparse Motion Estimation. In: 20th IEEE International Conference on Image Processing (2013)Google Scholar
  8. 8.
    Eiselein, V., Arp, D., Paetzold, M., Sikora, T.: Real-time Multi-human Tracking using a Probability Hypothesis Density Filter and Multiple Detectors. In: IEEE AVSS (2012)Google Scholar
  9. 9.
    Kuhn, A., Senst, T., Keller, I., Sikora, T., Theisel, H.: A Lagrangian Framework for Video Analytics. In: IEEE Workshop on Multimedia Signal Processing (2012)Google Scholar
  10. 10.
    Acar, E., Senst, T., Kuhn, A., Keller, I., Theisel, H., Albayrak, S., Sikora, T.: Human Action Recognition using Lagrangian Descriptors. In: IEEE MMSP (2012)Google Scholar
  11. 11.
    Open Network Video Interface Forum, http://www.onvif.org
  12. 12.
    Senst, T., Paetzold, M., Evangelio, R.H., Eiselein, V., Keller, I., Sikora, T.: On building decentralized wide-area surveillance networks based on ONVIF. In: IEEE AVSS (2011)Google Scholar
  13. 13.
    Pan, J.: A flexible ontology reasoning architecture for the semantic web. IEEE Transactions on Knowledge and Data Engineering 19(2), 246–260 (2007)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Richard Adderley
    • 1
  • Atta Badii
    • 2
  • Rubén Heras Evangelio
    • 3
  • Matteo Raffaelli
    • 4
  • Patrick Seidler
    • 1
  • Marco Tiemann
    • 2
  1. 1.A E Solutions (BI) Ltd.BadseyUK
  2. 2.University of ReadingReadingUK
  3. 3.Technische Universität BerlinBerlinGermany
  4. 4.Synthema srlPisaItaly

Personalised recommendations