Package boofcv.factory.background

Class ConfigBackgroundGmm

java.lang.Object

boofcv.factory.background.BaseConfigBackground

boofcv.factory.background.ConfigBackgroundGmm

All Implemented Interfaces:

Configuration, Serializable

public class ConfigBackgroundGmm
extends BaseConfigBackground

Configuration for ConfigBackgroundGmm.

Tuning Advice: Background models do a much better job of deciding if pixel doesn't match a model it has. This background model has multiple Gaussians. So you should keep the number of Gaussians small so that when the moving object goes past it doesn't because part of the model right away. If you have too many Gaussians its basically impossible to keep the amount of noise down and have a stable foreground object.

See Also:

• Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
float	decayCoefient	Determines how quickly a model is forgotten.
float	initialVariance	The initial variance assigned to a new pixel.
float	learningPeriod	Specifies how fast it will adjust to changes in the image.
float	maxDistance	Maximum Mahalanobis a value can be from a Gaussian to be considered a member of the gaussian
int	numberOfGaussian	Maximum number of gaussians that can be in a single mixture
float	significantWeight	Once the weight for a Gaussian becomes greater than this amount it is no longer considered part of the foreground and is the the background model.

Fields inherited from class boofcv.factory.background.BaseConfigBackground

unknownValue

Constructor Summary

Constructors

Constructor	Description
ConfigBackgroundGmm()

Method Summary

Modifier and Type	Method	Description
void	checkValidity()	Checks to see if the configuration is valid.
ConfigBackgroundGmm	setTo(ConfigBackgroundGmm src)
String	toString()

Methods inherited from class boofcv.factory.background.BaseConfigBackground

setTo

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface boofcv.struct.Configuration

serializeActiveFields, serializeInitialize

Field Details

learningPeriod

public float learningPeriod

Specifies how fast it will adjust to changes in the image. Must be greater than zero.

initialVariance

public float initialVariance

The initial variance assigned to a new pixel. Larger values to reduce false positives due to under sampling. Don't set to zero since that can cause divided by zero errors.

decayCoefient

public float decayCoefient

Determines how quickly a model is forgotten. Smaller values means they last longer. Values equal to or greater than one might cause new Gaussians to be immediately removed.

maxDistance

public float maxDistance

Maximum Mahalanobis a value can be from a Gaussian to be considered a member of the gaussian

numberOfGaussian

public int numberOfGaussian

Maximum number of gaussians that can be in a single mixture

significantWeight

public float significantWeight

Once the weight for a Gaussian becomes greater than this amount it is no longer considered part of the foreground and is the the background model. Strongly influences how long it takes an object that was moving to fade into the background. Probably one of the first tuning variables you should mess with.

Constructor Details

ConfigBackgroundGmm

public ConfigBackgroundGmm()

Method Details

setTo

public ConfigBackgroundGmm setTo(ConfigBackgroundGmm src)

checkValidity

public void checkValidity()

Description copied from interface: Configuration

Checks to see if the configuration is valid. If it is invalid, throw an exception explaining what is incorrect.

toString

public String toString()

Overrides:

toString in class Object