[attachment=14286]
Implementation of Video Surveillance Recording System using Normalized Cross Correlation (NCC) and Sum of Absolute Difference (SAD)
Abstract—
Research in motion analysis has evolved over the years as a challenging field, such as traffic monitoring, military, medicine and biological sciences etc. Detection of moving objects in video sequences can offer significant benefits to motion analysis. In today’s competitive environment, the security concerns have grown tremendously. Hence, it is imperative for one to be able to safeguard one’s property from worldly harms such as thefts, destruction of property, people with malicious intent etc. Due to the advent of technology in the modern world, the methodologies used by thieves and robbers for stealing has been improving exponentially. Therefore, it is necessary for the surveillance techniques to also improve with the changing world. With the improvement in mass media and various forms of communication, it is now possible to monitor and control the environment to the advantage of the owners of the property. The latest technologies used in the fight against thefts and destruction are the video surveillance and monitoring. By using the technologies, it is possible to monitor and capture every inch and second of the area in interest. Therefore, we have developed a methodology to detect the motion in a video stream. In this paper an approach is proposed for the detection of moving object in an image sequence. Two consecutive frames from image sequence are partitioned into four quadrants and then the Normalized Cross Correlation (NCC) is applied to each sub frame. The sub frame which has minimum value of NCC indicates the presence of moving object. Keywords— Motion detection, Video, Crime, Cross Correlation, Sum of Absolute Difference (SAD), MATLAB
1. INTRODUCTION
If you consider video in the simplest of terms, video surveillance began with simple closed circuit television monitoring (CCTV). As early as 1965, there were press reports in various countries across the world suggesting police use of surveillance cameras in public places. When videocassette recorders hit the market, video surveillance became really popular.
Analog technology using taped video-cassette recordings meant surveillance could be preserved on tape as evidence. A complete analog video- surveillance system consisted of a camera, monitor, and VCR. The old tube camera was only useful in daylight, and the VCR could only store eight hours of footage at best. The drawback was that after a while, owners and employees of such a system would become complacent and not change the tapes daily or the tapes would wear out after months of being re-used. There was also the problem of recording at night or in low light. While the concept was good, the technology hadn‟t yet peaked. The next step was the Charged Coupled Device camera (CCD), which used microchip computer technology. In the 1990‟s video surveillance made great strides in practicality by the introduction of digital multiplexing. When digital multiplexer units became affordable, it revolutionized the surveillance industry by enabling recording on several cameras at once (more than a dozen at time in most cases). Three key factors brought on the popular use of the digital video recorder. They are,
1. The advancement in compression capability, allowing more information to be stored on a hard drive. (Round the- clock surveillance produces a lot of information.)
2. The cost of a hard drive, which has dropped dramatically in recent years.
3. The storage capacity of a hard drive, which has increased dramatically in recent years.
Digital video surveillance made complete sense as the price of digital recording dropped with the computer revolution. Rather than changing tapes daily, the user could reliably record a month's worth of surveillance on hard drive. Normalized cross correlation (NCC) algorithm is based on finding the cross correlation between two consecutive frames in an image sequence. Correlation is basically used to find the similarity between two frames. If the two consecutive frames are exactly same, then the value of Normalized cross correlation is maximum. In that case no moving object is detected. Now suppose there is a moving object in the image sequence, means the two consecutive frames are not exactly same, with respect to positions of the pixel values. In that case the value of Normalized cross correlation is less than maximum value obtained. This concept of Normalized cross correlation is used for the detection of moving object in an image sequence.