Detection of Static and Dynamic Abnormal Activities in Crowded Areas Using Hybrid Clustering

  • M. R. Sumalatha
  • P. Lakshmi Harika
  • J. Aravind
  • S. Dhaarani
  • P. Rajavi
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 30)


In Computer Vision, to monitor the activities, behavior, and other changing information, surveillance is used. Surveillance is used by government organizations, private companies for security purposes. In video processing, anomaly is generally considered as a rarely occurring event. In a crowded area, it is impossible to monitor the occasionally moving objects and each person’s behavior. The main objective is to design a framework that detects the occasionally moving objects and abnormal human activities in the video. Histogram of Oriented Gradient feature extraction is used for the detection of an occasionally moving object and abnormality detection involves in computing the motion map by the flow of motion vectors in a scene that detects the change in movement. The experimental analysis demonstrates the effectiveness of this approach which is efficient to run in real time achieves 96% performance, however, for effective validation of the system is tested with standard UMN datasets and own datasets.


Hybrid clustering Occasionally moving object detection Uncommon human activity detection 


  1. 1.
    Lin K, Chen S-C, Chen C-S, Lin D-T, Hung Y-P (2015) Abandoned object detection via temporal consistency modeling and back-tracing verification for visual surveillance. IEEE Trans Inf Forensics Secur 10(7):1359–1370CrossRefGoogle Scholar
  2. 2.
    Lin C-Y, Muchtar K, Yeh C-H (2014) Grabcut-based abandoned object detection. In: IEEE 16th international workshop on multimedia signal processing (MMSP), pp1–6Google Scholar
  3. 3.
    Grab cut segmentation to extract foreground,
  4. 4.
  5. 5.
    Jadhav LH, Momin BF (2016) Detection and identification of unattended/removed objects in video surveillance. In: IEEE international conference on recent trends in electronics, information & communication technology, pp 1770–1773Google Scholar
  6. 6.
    Jaouedı N, Boujnah N, Htıwıch O, Bouhlel MS (2016) Human action recognition to human behavior analysis. In: 7th international conference on sciences of electronics, technologies of information and telecommunications, pp 263–266Google Scholar
  7. 7.
  8. 8.
    Kumar S, John M (2016) Human activity recognition using optical flow based feature set. In: IEEE international carnahan conference on security technology (ICCST), pp 1–5Google Scholar
  9. 9.
  10. 10.
    Zhu S, Xia L (2015) Human action recognition based on fusion features extraction of adaptive background subtraction and optical flow model. Math Probl Eng, Article id:387464, 2015:1–11 (2015) Scholar
  11. 11.
    Histogram of oriented gradients feature extraction,
  12. 12.
    Support Vector Machine (SVM), Scholar
  13. 13.
  14. 14.
  15. 15.
  16. 16.
  17. 17.
    ABODA Dataset Scholar
  18. 18.
  19. 19.
    Lin Y, Tong Y, Cao Y, Zhou Y, Wang S (2017) Visual- attention-based background modelling for detecting infrequently moving objects. IEEE Trans Circuits Syst Video Technol 27(6):1208–1221CrossRefGoogle Scholar
  20. 20.
    Lee D-G, Suk H-I, Park S-K, Lee S-W (2015) Motion influence map for unusual human activity detection and localization in crowded scenes. IEEE Trans Circuits Syst Video Technol 25(10):1612–1623CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Information TechnologyMIT Campus, Anna UniversityChennaiIndia

Personalised recommendations