Robust and Sensitive Video Motion Detection for security purpose analysis
Today theft and crimes rates are very high, so there is a significant need to monitor and monitor our property.
Cameras usage was limited to surveillance; nowadays we dont, merely, need to monitor our offices, banks and houses; but we also need to lessen and /or prevent damages; including as theft, and other types of crimes.
Cameras can track pedestrians, monitor traffic and city management, etc. These cameras send the video frames in real time to our system; the latter detects the moving objects within the frame, to decide whether the moving object is a human or not. The research aims to identify the requirements to develop an Anti-theft Camera real-time recorder for personal property surveillance, in addition to try and evaluate the proposed Anti-theft Camera real-time recorder system. Our goal is to discover and analyze the pedestrian (movement), whatever the lighting or camera angle , by analyzing the video then restart an alarm to prevent the thieves all in real time, even though if there are some factors of disruption .In this research we have developed a system to detect a moving objects within the video frame depend on developing subtracting the current image coming from the video frame from the stored reference image (or the previous image coming from the video frame); it is called "motion blocks detection". To lessen to complexity to become more effective in real time We have got relative highly precise results; (after conducting a trial over 50 moving objects within the image). The results approximate the 50 actually detected moving objects in the video. This has been achieved through improving and analyzing images taken from the video frame. We got a high accuracy results relatively, through applying multiple algorithms to detect motion within video frame.
S.S. Beauchemin and J.L.Barron, The Computation of Optical flow, ACM Computing Surveys, Vol.27, 1995, pp 433 466
Y.L.Tian and A.Hampapur, Robust Salient Motion Detection with Complex Background for Real-time Video Surveillance, in Proc. Of IEEE Computer Society Workshop on Motion and Video Computing, January, 2005
Qiang Zhu1, Shai Avidan2. Fast Human Detection Using a Cascade of Histograms of Oriented Gradients University of California at Santa Barbara, CA, 93106, USA 2007.
David S. Bolme Simple Real-Time Human Detection Using a Single Correlation Filter Colorado State University Fort Collins, CO 80521, USA 2010.
Dr. Florian Raudies, Boston University, Boston, MA, USA
http://www.scholarpedia.org/article/Optic_flow Last Update 12/6/2014
Ahmed Elgammal, David Harwood.. Non-parametric Model for Background Subtraction, Lecture Notes in Computer Science Volume 1843, 2000, pp 751-767
A. J. Smola and B. Schlkopf, A tutorial on support vector regression, Stat. Comput. 2004, 14, 199-222.
Staffan Reinius, Object recognition using cascade-classifier uppsala university 2013
David S. Bolme. Computer Vision and Pattern Recognition, IEEE 2009.
Feng Wang. A Robust Blob Recognition and Tracking Method in Vision-based Multitouch Technique 2008.
Su Juan A scene matching algorithm based on SURF feature IEEE 2010
Copyright (c) 2015 Journal of Information Sciences and Computing Technologies
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
TRANSFER OF COPYRIGHT
JISCT is pleased to undertake the publication of your contribution to Journal of Information Sciences and Computing Technologies
The copyright to this article is transferred to JISCT(including without limitation, the right to publish the work in whole or in part in any and all forms of media, now or hereafter known) effective if and when the article is accepted for publication thus granting JISCT all rights for the work so that both parties may be protected from the consequences of unauthorized use.