An Efficient Hybrid Approach for Detecting and Tracking Moving Objects for Video Surveillance

  • S. Shanmugappriya Research Scholar Alagappa University,
  • K. Mahesh Professor Department of Computer Applications,Alagappa University
DOI: https://doi.org/10.53555/cse.v3i5.497
Keywords: Object detection;, Wiener Filter, Background Difference, Gaussian Mixture, YCbCr

Abstract

In visual surveillance applications, detection and identification of an object in video frames
stream is to be considered as critical task. In recent years, researchers designed many algorithms
named Background Subtraction, Optical Flow and Temporal Differencing, etc., to detecting the
real time moving object. Among these, background subtraction algorithm used widely because it
has frame difference, approximate median, Gaussian mixture. The aim of the proposed work is to
detect real time moving objects could be done efficacy with the help of mixture of Gaussian
algorithm which requires less in memory and produce good in result. Here, unwanted noise can
be removed by using wiener filter, select YCbCr color space for detecting the foreground object
which is fit for light / indoor shadow. Further, test has been made on various video clip and from
the experimental results, complexity is easily reduce as well as foreground objects are detected
without noise by using Gaussian mixture model.

Downloads

Download data is not yet available.

Author Biographies

S. Shanmugappriya, Research Scholar Alagappa University,

Department of Computer Applications,Alagappa University, Karaikudi-600 003, Tamilnadu, India.

K. Mahesh, Professor Department of Computer Applications,Alagappa University

Professor Department of Computer Applications,Alagappa University, Karaikudi-600 003, Tamilnadu, India.


Published
2017-05-31
How to Cite
Shanmugappriya, S., & Mahesh, K. (2017). An Efficient Hybrid Approach for Detecting and Tracking Moving Objects for Video Surveillance. IJRDO -Journal of Computer Science Engineering, 3(5). https://doi.org/10.53555/cse.v3i5.497
Issue
Vol. 3 No. 5 (2017): IJRDO - Journal of Computer Science Engineering
Section
Articles

Author(s) and co-author(s) jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties, and that the Article has not been published elsewhere. Author(s) agree to the terms that the IJRDO Journal will have the full right to remove the published article on any misconduct found in the published article.