boofcv.factory.background

Class ConfigBackgroundGaussian

java.lang.Object

boofcv.factory.background.ConfigBackgroundGaussian

All Implemented Interfaces:

boofcv.struct.Configuration, java.io.Serializable

public class ConfigBackgroundGaussian
extends java.lang.Object
implements boofcv.struct.Configuration

Configuration for ConfigBackgroundGaussian.

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
float	initialVariance The initial variance assigned to a new pixel.
boofcv.alg.interpolate.InterpolationType	interpolation Specifies which interpolation it will use.
float	learnRate Specifies how fast it will adapt to changes in the background.
float	minimumDifference Minimum Euclidean distance between the mean background and observed pixel value for it to be considered moving.
float	threshold Threshold for classifying a pixel as background or not.

Constructor Summary

Constructors

Constructor and Description
ConfigBackgroundGaussian(float threshold)
ConfigBackgroundGaussian(float threshold, float learnRate)

Method Summary

Modifier and Type	Method and Description
void	checkValidity()

Methods inherited from class java.lang.Object

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

Field Detail

learnRate

public float learnRate

Specifies how fast it will adapt to changes in the background. From 0 to 1, inclusive. 0 = static 1.0 = instant.

threshold

public float threshold

Threshold for classifying a pixel as background or not. This threshold is applied to the computed Mahalanobis from the distribution. An appropriate threshold will vary depending on the number of bands in the image.

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.

minimumDifference

public float minimumDifference

Minimum Euclidean distance between the mean background and observed pixel value for it to be considered moving. This value is automatically scaled for the number of bands in the image.

interpolation

public boofcv.alg.interpolate.InterpolationType interpolation

Specifies which interpolation it will use. InterpolationType.BILINEAR or InterpolationType.NEAREST_NEIGHBOR recommended.

ONLY USED FOR MOVING BACKGROUNDS!

Constructor Detail

ConfigBackgroundGaussian

public ConfigBackgroundGaussian(float threshold)

ConfigBackgroundGaussian

public ConfigBackgroundGaussian(float threshold,
                                float learnRate)

Method Detail

checkValidity

public void checkValidity()

Specified by:

checkValidity in interface boofcv.struct.Configuration