Motion Detection based recording in Video Surveillance

System

Abstract:
The main goal of this project is to record the video in video surveillance system when
there is some event/movement in the video. This could be achieved by using the motion
detection algorithm to detect movement in the video. Whenever there is a movement in
the surveillance area then only recording of the video starts, the recording ends when the
there is no movement and finally the video saved as a new file.

Existing System:

Proposed System:

Introduction:
There are many approaches for motion detection in a continuous video stream. All of
them are based on comparing of the current video frame with one from the previous
frames or with the background
Among all The most efficient algorithms are based on building the background of the
scene and comparing each current frame with the background.
Here an original 24 bpp RGB image called current frame ,a grayscale copy of it and a
background frame also gray scaled .At the beginning, we get the first frame of the video
sequence as the background frame. And then we'll always compare the current frame with
the background one.Our approach is to "move" the background frame to the current
frame on the specified amount (here we use 1 level per frame). We move the background
frame slightly in the direction of the current frame i.e we are changing colors of pixels in
the background frame by one level per frame.From this approach we will get the objects
that are highlighted with a curve, which represents the moving object's boundary.
There is another approach based on the idea. As in the previous cases, we have an
original frame and a gray scaled version of it and of the background frame. Now we
apply Pixellate filter to the current frame and to the background to get pixellated
versions of both before further processing. Now, we need to move the background frame
towards the current frame as done before. The next change is only the main processing
step: We use "BlobCounter" to get the number of objects, their position and the
dimension on a binary image.From this approach we will get a rectangle of the object ,
which not only just highlight the objects, but also gives their count, position, width and
height
"Morph filter" is used for updating background image.This filter is used to preserve
specified percentage of the source filter and to add missing percentage from overlay
image.( So, if the filter was applied to source image with percent value equal to 60%,
then the result image will contain 60% of source image and 40% of overlay image.)
Applying the filter with percent values around 90% makes background image changing
continuously to current frame
We can also add motion alarm feature to both the approaches specified above. In each we
calculate a binary image containing difference between current frame and the background
one that gives the amount of white pixels on the difference image.In blob counting
approach we can accumulate not the white pixels count, but the area of each detected
object. Then, if the computed amount of changes is greater than a predefined value, we
can fire an alarm event.

To process the motion alarm event: The most useful is video saving on motion detection.
Here we use "AVIWriter" class, which uses "Video" for "Windows" interop to
provide AVI files saving capabilities.

The Motion Detection application is based on the "AForge.NET" framework, which

provides all the filters and image processing routines used in this application. .
This application supports the following types of video sources:
• AVI files
• updating JPEG from internet cameras;
• MJPEG (motion JPEG) streams from different internet cameras;
• local capture device (USB cameras or other capture devices)
Requirements:
Software Requirements:
• Microsoft Visual Studio .NET Frame work
• Microsoft Visual Studio C#.NET
• AForge.NET Framework
• Windows XP Operating System

Hardware Requirements:
• USB Cameras / Web Cam
• Minimum: 400 MHz CPU, 96 MB RAM, 800x600 256-color display
• Recommended: 1.0 GHz or higher CPU, 256 MB or more RAM, 1024x768
high-color 32-bit display
• Up to 500 MB of hard disk space may be required