The week's pick
Random Articles
Reseach Article
An Intelligent Suspicious Activity Detection Framework (ISADF) for Video Surveillance Systems
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 84 - Number 14 |
| Year of Publication: 2013 |
| Authors: Dammalapati Neelima, Gera Jaideep, Gera Indira Priyadharsani |
10.5120/14644-2941
|
Dammalapati Neelima, Gera Jaideep, Gera Indira Priyadharsani . An Intelligent Suspicious Activity Detection Framework (ISADF) for Video Surveillance Systems. International Journal of Computer Applications. 84, 14 ( December 2013), 26-30. DOI=10.5120/14644-2941
Abstract
Video Surveillance systems are playing vital role in ensuring the security at various public places like bus stops, railway stations, shopping malls, Airports etc. Suspicious activity recognition helps to prevent from threats and identify the causes after threat. Existing semi-automatic approaches depends on human intervention to detect the uncommon activities and suspicious behavior from video context. Due to these limitations they become non-intelligence, very slow and need more human observers. In this paper, to overcome these problems an Intelligent Suspicious Activity Detection Framework (ISADF) for Video data is proposed. This framework uses location dependent training data for intelligence and context (foreground) change information for suspicious activity detection. Experimental results show that ISADF is a high speed intelligent threat detection system than existing approaches.
References
- AACH, T. – KAUP, A. : "Statistical Model-Based Change Detection in Moving Video", Signal Processing, 31, pp. 165–180, 1993.
- BOJKOVIc, Z. – SAMcOVIc, A. – TURÁN, T:"Object Detection and Tracking in Video Surveillance Systems", COST 276 Workshop, Trondheim, Norvegia, pp. 113–116, May 25–26, 2005.
- R. Collins, Y. Tsin, J. R. Miller, and A. Lipton. Using a DEM to determine geospatial object trajectories. InProceedings of the 1998 DARPA Image Understanding Workshop, pages 115– 122, November 1998.
- Hae-Min Moon, Sumg Bum Pan:" A New Human Identification Method for Intelligent Video Surveillance System", 978-1-4244-7116-4/10, 2010 IEEE.
- http://www. imsresearch. com/research-areas.
- T. B Moelsund,A . Hilson, and V Kruger, " A Survey of Advances in vision based human motion capture and Analysis" Computer vision and image understanding special issue, vol-104,no 2-3,pp. 90-126,2006.
- A. Mittal and D. Huttenlocher, "Scene modelling for wide area surveillance and image synthesis," in Proceedings IEEE conference on computer vision and pattern recognition ,2 ,pp. 160{167, (Hilton Head Isand, SC), June 2000.
- T. Kanade, R. Collins, A. Lipton, P. Anandan, and P. Burt. Cooperative multisensor video surveillance. In Proceedings of the 1997 DARPA Image Understanding Workshop, volume 1, pages 3–10, May 1997.
- " Incremental and adaptive normal behavior detection " by X. Tao and G. Shaogang from computer vision and understanding , vol. 111 , no. 1 ,pp 59-73, 2008.
- Massimo Piccardi, "Background subtraction techniques: a review", IEEE International Conference on Systems, man and cybernets 2004.
- " Multi Feature path modeling for video surveillance " by junejo, javed, shah in ICPR proceedings of the 17th International conference. VOL 2. PP. 716-719. vol2. 2004.
- A . Viswani , Roychowdary and challappa "activity recognition using the dynamics of the configuration of interaction objects" IEEE computer science society conference on, vol 2,pp 923-926. vol 2. 2004.
- HU. Yan Remote sensing image classification based on SVM classifier System Science, Engineering Design and Manufacturing Informatization (ICSEM), 2011 International Conference on (Volume:1 ) oct 2011.
- c. shuldt, laptev and capturo " Recognizing human actions : a local svm approach" in pattern reconization. ICPR proceedings of 17th international conference on vol 3,pp 32-36,2004.
Index Terms
Keywords