Motion Detection
The page describes deprecated features, which are available only in 1.7.0 version
of the framework. Visit the next page for information about new
motion detection classes.
AForge.NET framework provides set of classes aimed to do motion detection in
video streams. All the classes implement fairly simple and common interface, which is actually
not bound to any specific video stream format/protocol. Instead of this, these classes just
analyze consequent video frames given by user, which makes them free from any video processing
routines and makes them applicable to any video stream format.
Different motion detection classes may use different algorithms to detect motion. But they
are all similar in the way how they get video frames to analyze and how they report about
detected motion level. All these class provide motion level property, which is the level of
motion in the [0, 1] range. For example, if the property says 0.05, then it means that motion
detection class has detected 5% motion level. Analyzing this property and comparing it with
predefined threshold allows to raise alarm, when detected motion level is greater then the level
which is considered to be safe.
Below is a simple code sample, which demonstrates main idea of working with different motion
detector.
// create motion detector with noise suppresion
IMotionDetector detector = new ... (specific motion detection class)
// feed video frame to the detector
while ( !needToStop )
{
// feed video frame
detector.ProcessFrame( videoFrame );
// check motion level
if ( detector.MotionLevel > 0.01 )
{
// motion level is greater then 1% - fire alarm
// make sound, start blinking, start saving video, etc.
// ...
}
}
As the code shows, all we need to do is to feed new video frame and then check motion level.
Note: user's code is responsible for reading video frames from particular stream, which makes
motion detectors decoupled from video reading. See AForge.Video namespace
for classes to access different video stream.
In addition to motion level detection, all motion detectors support highlighting of detected
motion regions (can be turned on/off. But this really depends on particular detector, since
highlighting may be done differently depending on algorithms use by detector.
Two frames difference motion detector
This type of motion detector is the simplest one and the quickest one. The idea of this detector is
based on finding amount of difference in two consequent frames of video stream. The greater is difference,
the greater is motion level. As it can be seen from the picture below, it does not suite very well those
tasks, where it is required to precisely highlight moving object. However it has recommended itself very well
for those tasks, which just require motion detection.
Motion detectors based on background modeling
In contrast to the above motion detector, these motion detectors are based on finding difference between current
video frame and a frame representing background. These motion detectors try to use simple techniques of modeling
scene's background and updating it through time to get into account scene's changes. The background modeling
feature of these motion detectors gives the ability of more precise highlighting of motion regions.
Below are demonstrated output of two versions of motion detectors based on background modeling. One does more
precise highlight of moving objects' borders, but consumes more computational resources. Another one does less
precise objects' highlight in the cost of requiring much less computational resources.
Counting motion detector
The counting motion detector is based on the same idea of background modeling as the above motion detectors.
However after that it does additional processing and different object's highlighting. Once motion regions
are identified, this detector uses blob counting algorithm to find rectangles of each detected moving object.
This gives the ability to report about amount of detected objects, as well as position and size of each detected object (which are provided by additional properties of the motion detector class).
In addition to counting feature, this motion detector also supports rectangular zones of interest. It is possible
to specify regions of video frames, where the algorithm should work on detecting motion. All the rest of video
frame, which is not part of specified regions, is ignored and motion level is not reported for those parts.
| 
