SimpleBackgroundModelingDetector Class |
Namespace: Accord.Vision.Motion
The SimpleBackgroundModelingDetector type exposes the following members.
Name | Description | |
---|---|---|
SimpleBackgroundModelingDetector |
Initializes a new instance of the SimpleBackgroundModelingDetector class.
| |
SimpleBackgroundModelingDetector(Boolean) |
Initializes a new instance of the SimpleBackgroundModelingDetector class.
| |
SimpleBackgroundModelingDetector(Boolean, Boolean) |
Initializes a new instance of the SimpleBackgroundModelingDetector class.
|
Name | Description | |
---|---|---|
DifferenceThreshold |
Difference threshold value, [1, 255].
| |
FramesPerBackgroundUpdate |
Frames per background update, [1, 50].
| |
KeepObjectsEdges |
Restore objects edges after noise suppression or not.
| |
MillisecondsPerBackgroundUpdate |
Milliseconds per background update, [0, 5000].
| |
MotionFrame |
Motion frame containing detected areas of motion.
| |
MotionLevel |
Motion level value, [0, 1].
| |
SuppressNoise |
Suppress noise in video frames or not.
|
Name | Description | |
---|---|---|
Equals | Determines whether the specified object is equal to the current object. (Inherited from Object.) | |
Finalize | Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (Inherited from Object.) | |
GetHashCode | Serves as the default hash function. (Inherited from Object.) | |
GetType | Gets the Type of the current instance. (Inherited from Object.) | |
MemberwiseClone | Creates a shallow copy of the current Object. (Inherited from Object.) | |
ProcessFrame |
Process new video frame.
| |
Reset |
Reset motion detector to initial state.
| |
ToString | Returns a string that represents the current object. (Inherited from Object.) |
Name | Description | |
---|---|---|
HasMethod |
Checks whether an object implements a method with the given name.
(Defined by ExtensionMethods.) | |
IsEqual |
Compares two objects for equality, performing an elementwise
comparison if the elements are vectors or matrices.
(Defined by Matrix.) | |
To(Type) | Overloaded.
Converts an object into another type, irrespective of whether
the conversion can be done at compile time or not. This can be
used to convert generic types to numeric types during runtime.
(Defined by ExtensionMethods.) | |
ToT | Overloaded.
Converts an object into another type, irrespective of whether
the conversion can be done at compile time or not. This can be
used to convert generic types to numeric types during runtime.
(Defined by ExtensionMethods.) |
The class implements motion detection algorithm, which is based on difference of current video frame with modeled background frame. The difference frame is thresholded and the amount of difference pixels is calculated. To suppress stand-alone noisy pixels erosion morphological operator may be applied, which is controlled by SuppressNoise property.
Note |
---|
In the case if precise motion area's borders are required (for example, for further motion post processing), then KeepObjectsEdges property may be used to restore borders after noise suppression. |
As the first approximation of background frame, the first frame of video stream is taken. During further video processing the background frame is constantly updated, so it changes in the direction to decrease difference with current video frame (the background frame is moved towards current frame). See FramesPerBackgroundUpdateMillisecondsPerBackgroundUpdate properties, which control the rate of background frame update.
Unlike TwoFramesDifferenceDetector motion detection algorithm, this algorithm allows to identify quite clearly all objects, which are not part of the background (scene) - most likely moving objects. And unlike CustomFrameDifferenceDetector motion detection algorithm, this algorithm includes background adaptation feature, which allows it to update its modeled background frame in order to take scene changes into account.
Note |
---|
Because of the adaptation feature of the algorithm, it may adopt to background changes, what CustomFrameDifferenceDetector algorithm can not do. However, if moving object stays on the scene for a while (so algorithm adopts to it and does not treat it as a new moving object any more) and then starts to move again, the algorithm may find two moving objects - the true one, which is really moving, and the false one, which does not (the place, where the object stayed for a while). |
Note |
---|
The algorithm is not applicable to such cases, when moving object resides in camera's view most of the time (laptops camera monitoring a person sitting in front of it, for example). The algorithm is mostly supposed for cases, when camera monitors some sort of static scene, where moving objects appear from time to time - street, road, corridor, etc. |
Sample usage:
// create motion detector MotionDetector detector = new MotionDetector( new SimpleBackgroundModelingDetector( ), new MotionAreaHighlighting( ) ); // continuously feed video frames to motion detector while ( ... ) { // process new video frame and check motion level if ( detector.ProcessFrame( videoFrame ) > 0.02 ) { // ring alarm or do somethng else } }