Package boofcv.abst.feature.detect.interest

Class ConfigFastHessian

java.lang.Object

boofcv.abst.feature.detect.interest.ConfigFastHessian

All Implemented Interfaces:

Configuration, Serializable

public class ConfigFastHessian
extends Object
implements Configuration

Configuration for FastHessianFeatureDetector plus feature extractor.

See Also:

• Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
ConfigExtract	extract	Configuration for non-maximum thresholding
int	initialSampleStep	How often pixels are sampled in the first octave.
int	initialSize	Typically 9.
int	maxFeaturesAll	Maximum number of features it will return in total.
int	maxFeaturesPerScale	The maximum number of features it can detect in a single scale.
int	numberOfOctaves	Typically 4.
int	numberScalesPerOctave	Typically 4.
int	scaleStepSize	Increment between kernel sizes as it goes up in scale.
ConfigSelectLimit	selector	Approach used to select features when more than the maximum have been detected

Constructor Summary

Constructors

Constructor	Description
ConfigFastHessian()
ConfigFastHessian(float detectThreshold, int extractRadius, int maxFeaturesPerScale, int initialSampleStep, int initialSize, int numberScalesPerOctave, int numberOfOctaves)

Method Summary

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

Methods inherited from class java.lang.Object

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

Methods inherited from interface boofcv.struct.Configuration

serializeActiveFields, serializeInitialize

Field Details

extract

public ConfigExtract extract

Configuration for non-maximum thresholding

maxFeaturesPerScale

public int maxFeaturesPerScale

The maximum number of features it can detect in a single scale. Useful if you want to prevent high frequency features from dominating. If ≤ 0 then it will have no limit.

maxFeaturesAll

public int maxFeaturesAll

Maximum number of features it will return in total. If ≤ 0 then it will have no limit.

selector

public ConfigSelectLimit selector

Approach used to select features when more than the maximum have been detected

initialSampleStep

public int initialSampleStep

How often pixels are sampled in the first octave. Typically 1 or 2.

initialSize

public int initialSize

Typically 9.

numberScalesPerOctave

public int numberScalesPerOctave

Typically 4.

numberOfOctaves

public int numberOfOctaves

Typically 4.

scaleStepSize

public int scaleStepSize

Increment between kernel sizes as it goes up in scale. In some data sets, increasing this value beyound the default value results in an improvement in stability. Default 6

Constructor Details

ConfigFastHessian

public ConfigFastHessian(float detectThreshold,
 int extractRadius,
 int maxFeaturesPerScale,
 int initialSampleStep,
 int initialSize,
 int numberScalesPerOctave,
 int numberOfOctaves)

ConfigFastHessian

public ConfigFastHessian()

Method Details

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.

Specified by:

checkValidity in interface Configuration

setTo

public ConfigFastHessian setTo(ConfigFastHessian src)

copy

public ConfigFastHessian copy()