Human Action Classification and Unusual Action Recognition Algorithm for Intelligent Surveillance System

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 215)

Abstract

This paper suggests an algorithm to classify human actions for the intelligent surveillance system. In order to classify actions, the proposed method calculates the difference image between input images and modeled background, uses motion information histogram and traces of center points of objects. Human actions are categorized into four types: they are the most frequently three actions people take walking, sitting, standing up and unusual action like as sudden falling down. We examine the proposed method on eight people with a sequence captured by using a web camera and the result shows that the proposed method classifies human actions well and recognitions of the unusual action.

Keywords

Silhouette Object tracking Auto detection Surveillance 

Notes

Acknowledgments

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science and Technology (2012-0002852).

References

  1. 1.
    Ayers D, Shah M (1998) Monitoring human behavior in an office environment. In: Computer society workshop on interpretation of visual motionGoogle Scholar
  2. 2.
    Robertson NM, Reid ID (2006) A general method for human activity in video. Comput Vis Image Underst 104:232–248Google Scholar
  3. 3.
    Peursum P, Bui HH, Svetha V, Geoff W (2005) Robust recognition and segmentation of Human actions using HMMs with missing observation EURASIP J Appl Signal Process 13:2110–2126Google Scholar
  4. 4.
    Kellokumpu V, Pietikäinen M, Heikkilä (2005) Human activity recognition using sequences of postures. In: IAPR conference on machine vision applications, pp 570–573Google Scholar
  5. 5.
    Rota N, Thonnat M (2000) Video sequence interpretation for visual surveillance. In: 3rd IEEE international workshop on visual surveillance, VS’00, pp 59–67Google Scholar
  6. 6.
    Vu VT, Bremond F, Thonnat M (2003) Automatic video interpretation: a recognition algorithm for temporal scenarios based on pre-compiled scenario models. In: Third international conference on computer vision systems (ICVS 2003), Lecture notes in computer science (LNCS), vol 2626. Springer, Berlin, Graz, Austria. pp 44–53Google Scholar
  7. 7.
    Ayers D, Chellappa R (2000) Scenario recognition from video using a hierarchy of dynamic belief networks. In: ICPR, pp 1835–1838Google Scholar
  8. 8.
    Tao J, Tan YP (2004) A probabilistic reasoning approach to closed-room people monitoring. IEEE ISCAS 2:185–188Google Scholar
  9. 9.
    Utsumi A, Yang H, Ohya J (2000) Adaptive human motion tracking using non-symchronous multiple viewpoint observations. In: Proceedings of IEEE 15th international conference on pattern recognition, vol 4, pp 607–610Google Scholar
  10. 10.
    de Campos TE, Murray DW (2006) Regression- based hand pose estimation from multiple cameras. CVPR 1:782–789Google Scholar
  11. 11.
    Kim K, Chalidabhongse TH, Harwood D, Davis L (2005) Real-time foreground-background segmentation using codebook model. Real-time Imaging 11:167–256CrossRefGoogle Scholar
  12. 12.
    Rubner Y, Tomasi C, Guibas LJ (1998) A metric for distributions with applications to image databases. In: IEEE international conference on computer vision, pp 59–66, Jan 1998Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  1. 1.Department of Computer EngineeringMokwon UniversityDaejeonSouth Korea

Personalised recommendations