Advertisement

A Scalable Approach Based on Normality Components for Intelligent Surveillance

  • Javier Albusac
  • José J. Castro-Schez
  • David Vallejo
  • Luis Jiménez-Linares
  • Carlos Glez-Morcillo
Part of the Studies in Computational Intelligence book series (SCI, volume 336)

Abstract

Since their first developments, traditional video surveillance systems have been designed to monitor environments. However, these systems have several limitations to automatically understand events and behaviours without human collaboration. In order to overcome this problem, intelligent surveillance systems arise as a possible solution. This kind of systems are not affected by negative factors such as fatigue or tiredness and they can be more effective than people when recognising certain kinds of events, such as the detection of suspicious or unattended objects. Intelligent surveillance refers to using Artificial Intelligence and Computer Vision techniques in order to improve traditional surveillance and process semantic information, obtained from low-level security devices. Normally these systems consist of a set of independent analysis modules that deal with particular problems, such as the trajectory analysis of pedestrian in parking lots, speed estimation of vehicles, gait or facial recognition, etc. However, most of them present a common problem: lack of flexibility and scalability to include new kinds of analysis and combine all of them in order to obtain a global interpretation. In this work, a formal model to define normal events and behaviours in monitored environments and to build scalable surveillance systems is presented. This model is based on the use of normality components, which are independent and reusable for environments with different characteristics and different kinds of objects. Each component specifies how an object should ideally behave according to a surveillance aspect, such as trajectory or velocity. The model also includes the fusion mechanisms required for combining the particular analysis made by each component. Finally, when a new component is designed making use of the proposed model, the system increases its abilities to detect new kind of abnormal events, and the normality of an object depends on a higher number of factors.

Keywords

Surveillance System Monitor Environment Absolutely Normal Normal Trajectory Monitor Object 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
    Aguilera, J., Wildernauer, H., Kampel, M., Borg, M., Thirde, D., Ferryman, J.: Evaluation of motion segmentation quality for aircraft activity surveillance. In: IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 293–300 (2005)Google Scholar
  3. 3.
    Albusac, J., Castro-Schez, J.J., López-López, L.M., Vallejo, D., Jimenez, L.: A Supervised Learning Approach to Automate the Acquisition of Knowledge in Surveillance Systems. Signal Processing, Special issue on Visual Information Analysis for Security 89(12), 2400–2414 (2009)zbMATHGoogle Scholar
  4. 4.
    Allen, J., Ferguson, G.: Actions and Events in Interval Temporal Logic. Journal of Logic and Computation 4(5), 531–579 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Blauensteiner, P., Kampel, M.: Visual Surveillance of an Airports Apron-An Overview of the AVITRACK Project. In: Annual Workshop of AAPR, Digital Imaging in Media and Education, pp. 1–8 (2004)Google Scholar
  6. 6.
    Bloisi, D., Iocchi, L., Bloisi, D., Iocchi, L., Remagnino, P., Monekosso, D.N.: ARGOS–A Video Surveillance System for Boat Traffic Monitoring in Venice. International Journal of Pattern Recognition and Artificial Intelligence 23(7), 1477–1502 (2009)CrossRefGoogle Scholar
  7. 7.
    Buxton, H.: Learning and understanding dynamic scene activity: a review. Image and Vision Computing 21(1), 125–136 (2003)CrossRefGoogle Scholar
  8. 8.
    Carter, N., Young, D., Ferryman, J.: A combined Bayesian Markovian approach for behaviour recognition. In: Proceedings of the 18th International Conference on Pattern Recognition, pp. 761 –764 (2006)Google Scholar
  9. 9.
    Cathey, F., Dailey, D.: A novel technique to dynamically measure vehicle speed using uncalibrated roadway cameras. In: IEEE Intelligent Vehicles Symposium, pp. 777–782 (2005)Google Scholar
  10. 10.
    Chen, T., Haussecker, H., Bovyrin, A., Belenov, R., Rodyushkin, K., Kuranov, A., Eruhimov, V.: Computer vision workload analysis: Case study of video surveillance systems. Intel Technology Journal 9(2), 109–118 (2005)Google Scholar
  11. 11.
    Cho, Y., Rice, J.: Estimating velocity fields on a freeway from low-resolution videos. IEEE Transactions on Intelligent Transportation Systems 7(4), 463–469 (2006)CrossRefGoogle Scholar
  12. 12.
    Collins, R., Lipton, A., Kanade, T., Fujiyoshi, H., Duggins, D., Tsin, Y., Tolliver, D., Enomoto, N., Hasegawa, O., Burt, P., et al.: A System for video surveillance and monitoring (Technical report CMU-RI-TR-00-12). Tech. rep., Robotics Institute, Carnegie Mellon University (2000)Google Scholar
  13. 13.
    Dee, H., Velastin, S.: How close are we to solving the problem of automated visual surveillance? Machine Vision and Applications 19(5), 329–343 (2008)CrossRefGoogle Scholar
  14. 14.
    Fawcett, T.: Roc graphs: Notes and practical considerations for data mining researchers (Technical report hpl-2003-4). Tech. rep., HP Laboratories, Palo Alto, CA, USA (2003)Google Scholar
  15. 15.
    Franklin, W.: Pnpoly - point inclusion in polygon test (2006), http://www.ecse.rpi.edu/Homepages/wrf/Research/ShortNotes/pnpoly.html
  16. 16.
    Haritaoglu, I., Harwood, D., Davis, L.: W 4: Real-Time Surveillance of People and Their Activities. IEEE Transactions on Patter Analysis and Machine Intelligence 22(8), 809–830 (2000)CrossRefGoogle Scholar
  17. 17.
    Johnson, N., Hogg, D.: Learning the distribution of object trajectories for event recognition. Image and Vision Computing 14(8), 609–615 (1996)CrossRefGoogle Scholar
  18. 18.
    Khoudour, L., Deparis, J., Bruyelle, J., Cabestaing, F., Aubert, D., Bouchafa, S., Velastin, S., Vincencio-Silva, M., Wherett, M.: Project CROMATICA. In: Del Bimbo, A. (ed.) ICIAP 1997. LNCS, vol. 1311, pp. 757–764. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  19. 19.
    Lin, L., Gong, H., Li, L., Wang, L.: Semantic event representation and recognition using syntactic attribute graph grammar. Pattern Recognition Letters 30(2), 180–186 (2009)CrossRefGoogle Scholar
  20. 20.
    Maduro, C., Batista, K., Peixoto, P., Batista, J.: Estimation of vehicle velocity and traffic intensity using rectified images. In: Proceedings of the 15th IEEE International Conference on Image Processing (ICIP 2008), pp. 777–780 (2008)Google Scholar
  21. 21.
    Magee, D.: Tracking multiple vehicles using foreground, background and motion models. Image and Vision Computing 22(2), 143–155 (2004)CrossRefMathSciNetGoogle Scholar
  22. 22.
    Makris, D., Ellis, T.: Learning semantic scene models from observing activity in visual surveillance. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 35(3), 397–408 (2005)CrossRefGoogle Scholar
  23. 23.
    Morris, B., Trivedi, M.: A survey of vision-based trajectory learning and analysis for surveillance. IEEE Transactions on Circuits and Systems for Video Technology 18(8), 1114–1127 (2008)CrossRefGoogle Scholar
  24. 24.
    Palaio, H., Maduro, C., Batista, K., Batista, J.: Ground plane velocity estimation embedding rectification on a particle filter multi-target tracking. In: Proceedings of the 2009 IEEE International Conference on Robotics and Automation, pp. 2717–27722 (2009)Google Scholar
  25. 25.
    Piciarelli, C., Foresti, G.: On-line trajectory clustering for anomalous events detection. Pattern Recognition Letters 27(15), 1835–1842 (2006)CrossRefGoogle Scholar
  26. 26.
    Remagnino, P., Velastin, S., Foresti, G., Trivedi, M.: Novel concepts and challenges for the next generation of video surveillance systems. Machine Vision and Applications 18(3), 135–137 (2007)CrossRefGoogle Scholar
  27. 27.
    Shimrat, M.: Algorithm 112: Position of point relative to polygon. Communications of the ACM 5(8), 434 (1962)CrossRefGoogle Scholar
  28. 28.
    Siebel, N., Maybank, S.: Ground plane velocity estimation embedding rectification on a particle filter multi-target tracking. In: Proceedings of the ECCV Workshop Applications of Computer Vision, pp. 103–111 (2004)Google Scholar
  29. 29.
    Smith, G.: Behind the screens: Examining constructions of deviance and informal practices among cctv control room operators in the UK. Communications of the ACM 2(2), 376–395 (2004)Google Scholar
  30. 30.
    Sridhar, M., Cohn, A., Hogg, D.: Unsupervised Learning of Event Classes from Video. In: Proc. AAAI, AAAI Press, Menlo Park (to appear, 2010)Google Scholar
  31. 31.
    Valera, M., Velastin, S.: Intelligent distributed surveillance systems: a review. IEE Proceedings-Vision, Image and Signal Processing 152(2), 192–204 (2005)CrossRefGoogle Scholar
  32. 32.
    Vallejo, D., Albusac, J., Mateos, J., Glez-Morcillo, C., Jimenez, L.: A modern approach to multiagent development. Journal of Systems and Software 83(3), 467–484 (2009)CrossRefGoogle Scholar
  33. 33.
    Velastin, S., Khoudour, L., Lo, B., Sun, J., Vicencio-Silva, M.: PRISMATICA: a multi-sensor surveillance system for public transport networks. In: 12th IEE International Conference on Road Transport Information and Control, pp. 19–25 (2004)Google Scholar
  34. 34.
    Yager, R.: On ordered weighted averaging aggregation operators in multicriteria decisionmaking. IEEE Transactions on Systems, Man and Cybernetics 18(1), 183–190 (1988)zbMATHCrossRefMathSciNetGoogle Scholar
  35. 35.
    Yager, R.: Families of OWA operators. Fuzzy sets and systems 59(2), 125–148 (1993)zbMATHCrossRefMathSciNetGoogle Scholar
  36. 36.
    Zadeh, L.: Fuzzy sets. Information and Control 8(3), 338–353 (1965)zbMATHCrossRefMathSciNetGoogle Scholar
  37. 37.
    Zadeh, L.: From computing with numbers to computing with words - from manipulation of measurements to manipulation of perceptions. Circuits and Systems I: Fundamental Theory and Applications 46(1), 105–119 (1999)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Javier Albusac
    • 1
  • José J. Castro-Schez
    • 1
  • David Vallejo
    • 1
  • Luis Jiménez-Linares
    • 1
  • Carlos Glez-Morcillo
    • 1
  1. 1.University of Castilla-La ManchaCiudad RealSpain

Personalised recommendations