CFP last date
20 June 2024
Reseach Article

A Hybrid Motion Detection Algorithm in Video Surveillance

Published on March 2012 by Jyoti Wadmare
International Conference in Computational Intelligence
Foundation of Computer Science USA
ICCIA - Number 4
March 2012
Authors: Jyoti Wadmare
f354b496-b5ba-4409-9772-cce157865712

Jyoti Wadmare . A Hybrid Motion Detection Algorithm in Video Surveillance. International Conference in Computational Intelligence. ICCIA, 4 (March 2012), 26-30.

@article{
author = { Jyoti Wadmare },
title = { A Hybrid Motion Detection Algorithm in Video Surveillance },
journal = { International Conference in Computational Intelligence },
issue_date = { March 2012 },
volume = { ICCIA },
number = { 4 },
month = { March },
year = { 2012 },
issn = 0975-8887,
pages = { 26-30 },
numpages = 5,
url = { /proceedings/iccia/number4/5117-1029/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference in Computational Intelligence
%A Jyoti Wadmare
%T A Hybrid Motion Detection Algorithm in Video Surveillance
%J International Conference in Computational Intelligence
%@ 0975-8887
%V ICCIA
%N 4
%P 26-30
%D 2012
%I International Journal of Computer Applications
Abstract

Detection of moving objects in video streams is the first stage in many computer vision applications. Although this subject has been studied for many years, it is still a significant and difficult research problem. This paper proposes a hybrid motion detection algorithm which combines the temporal differencing, background subtraction and dynamic thresholding method together. As to which kind of temporal differencing technique or which kind of background model to take in our scheme, we can choose them flexibly according to concrete demands. In order to overcome the major drawback of background subtraction algorithm, which may cause false detection when stationary objects in the scene start to move, a temporal foreground mask is built and applied to adjust the initial detected results. Finally, several video sequences are tested to validate our hybrid algorithm. Experimental results show that our hybrid algorithm is very effective, which can satisfy the robustness of the moving object detection. Video synopsis can be created with the help of motion detection

References
  1. c. Anderson, Peter Burt, and G. vander Wal. "Change detection and tracking using pyramid transformation techniques", In Proceedings of SPIE - Intelligent Robots and Computer Vision, vol. 579, pp. 72-78, 1985.
  2. C. Stauffer, W.E. Grimson. "Adaptive Background Mixture Models for Real-time Tracking", CVPR99, 1999.
  3. A.M. Elgammal, D. Harwood, and L.S. Davis, "Non- Parametric Model for Background Subtraction", Proc. European Conf. Computer Vision, pp. 751-767,2000.
  4. R.T. Collins., AJ. Lipton, et al. "A System for Video Surveillance and Monitoring", The Robotics Institute, Pittsburgh, USA, 2000
  5. H.M. Wu, X. H. Zheng. "A new thresholding method applied to Motion Detection", Pacific-Asia Workshop on Computational Intelligence and Industrial Application, computer society, pp. 119-122,2008.
  6. K. Toyama, J. Krumm, B. Brumitt, and B. Meyers. "Wallflower: Principles and practice of background maintenance", In Proc. International Conference on Computer Vision, pp. 255-261,1999.
  7. T. Matsuyama, T. Ohya, H. Habe, “Background Subtraction for Non-Stationary Scenes,” Kyoto, Japan, 2000.
  8. M. Seki, H. Fujiwara, K. Sumi, “A Robust Background Subtraction Method for Changing Background,” IEEE Japan, 2000.
Index Terms

Computer Science
Information Sciences

Keywords

Motion detection Thresholding segmentation Hybrid algorithm