(44-3) 20 * << * >> * Russian * English * Content * All Issues

Incremental learning of an abnormal behavior detection algorithm based on principal components
R.A. Shatalin 1, V.R. Fidelman 1, P.E. Ovchinnikov 1

1 Lobachevsky State University of Nizhny Novgorod, Nizny Novgorod, Russia

 PDF, 749 kB

DOI: 10.18287/2412-6179-CO-624

Pages: 476-481.

Full text of article: Russian language.

Abstract:
In this paper, we propose an incremental learning scheme for the abnormal behavior detection algorithm based on principal component. The results obtained on a UCSD dataset and our experimental videos at a different number of training samples show that error rates are similar to conventional learning. Moreover, the proposed scheme allows the incremental learning time to be significantly reduced in comparison with a method based on matrix eigendecomposition.

Keywords:
incremental learning, video analysis, anomaly detection, principal component analysis.

Citation:
Shatalin RA, Fidelman VR, Ovchinnikov PE. Incremental learning for abnormal behaviour detection algorithm based on principal components. Computer Optics 2020; 44(3): 476-481. DOI: 10.18287/2412-6179-CO-624.

References:
  1. Popoola O, Wang K. Video-based abnormal human behavior recognition – A review. IEEE Trans Syst Man Cybern C 2012; 42(6): 865-878.
  2. Epifancev BN, Pyatkov AA, Kopeykin SA. Multi-sensor systems for monitoring access to restricted areas: capabilities of the intrusion detection video analytical channel. Computer Optics 2016; 40(1): 121-129. DOI: 10.18287/2412-6179-2016-40-1-121-129.
  3. Sodemann A, Ross M, Borghetti B. A review of anomaly detection in automated surveillance. IEEE Trans Syst Man Cybern C 2012; 42(6): 1257-1272.
  4. Jolliffe IT. Principal component analysis. 2nd ed. New York: Springer; 2002.
  5. Shatalin RA, Fidelman VR, Ovchinnikov PE. Abnormal behaviour detection method for video surveillance applications. Computer Optics 2017; 41(1): 37-45. DOI: 10.18287/2412-6179-2017-41-1-37-45.
  6. Losing V, Hammer B, Wersing H. Incremental on-line learning: A review and comparison of state of the art algorithms. Neurocomputing, 2018, 275: 1261-1274.
  7. Maddalena L, Petrosino A. a self-organizing approach to background subtraction for visual surveillance application. IEEE Trans Image Proces 2008; 17(7): 1168-1177.
  8. Shatalin R, Ovchinnikov P. Background subtraction quality criterion based on morphological operations for behaviour anomaly detection [In Russian]. Control Syst Inform Technol 2014, 56(2):190-4.
  9. Bouguet JY. Pyramidal implementation of the Lucas Kanade feature tracker. Intel Corp 2000.
  10. Antonakaki P, Kosmopoulos D, Perantonis S. Detecting abnormal human behavior using multiple cameras. Signal Procces 2009, 89(9): 1723-1738.
  11. Mahadevan V, Li W, Bhalodia V, Vasconcelos N. Anomaly detection and localization in crowded scenes. IEEE Trans Pattern Anal Machine Intell, 2014, 36(1): 18-31.
  12. Press WH, Teukolsky SA, Vetterling WT, Flannery BP Numerical recipes: The Art of scientific computing. 3rd ed. New York: Cambridge University Press; 2007.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20