|
|
latest version v1.9 - last update 10 Apr 2010 |
|
The parameters for the class locationSearchEvaluation. More...
#include <ltiLocationSearchEvaluation.h>
Public Member Functions | |
| parameters () | |
| parameters (const parameters &other) | |
| ~parameters () | |
| const char * | getTypeName () const |
| parameters & | copy (const parameters &other) |
| parameters & | operator= (const parameters &other) |
| virtual functor::parameters * | clone () const |
| virtual bool | write (ioHandler &handler, const bool &complete=true) const |
| virtual bool | read (ioHandler &handler, const bool &complete=true) |
Public Attributes | |
| std::string | images |
| std::string | postfix |
| pyramidLocationSearch::parameters | minValues |
| pyramidLocationSearch::parameters | maxValues |
| float | stepAngle |
| float | stepScaling |
| float | firstScaling |
| float | lastScaling |
| float | firstAngle |
| float | lastAngle |
| bool | considerAngle |
| float | scaleTolerance |
| float | positionTolerance |
| float | angleTolerance |
Fitness measures | |
Value containing the 1D fitness measures to be computed. The constants defined here are:
This sequence is important, since it determines the positions of the single measures in the fitness output vector. If more fitness measures are selected than the inherited parameter fitnessSpaceDimensionality, then the first ones in this sequence will be selected. If less fitness measure are selected than the inherited parameter fitnessSpaceDimensionality, then the rest of the vector will be filled with zeros. The difference between the "*Repeatibility" and the "*Stable" measures is that the first ones are the number of stable locations normalized to the total number of locations, i.e. their maximal value will be always 1.0. The "*Stable" unnormalized fitness measures may be important to optimize in those applications that require many stable locations to work, and not only the major part of them. | |
| bool | numberOfLocations |
| bool | locationsReciprocal |
| bool | occupiedLevels |
| bool | time |
| bool | scaleRepeatability |
| bool | rotationRepeatability |
| bool | rotationScaleRepeatability |
| bool | scaleStable |
| bool | rotationStable |
| bool | rotationScaleStable |
The parameters for the class locationSearchEvaluation.
| lti::locationSearchEvaluation::parameters::parameters | ( | ) |
Default constructor.
Reimplemented from lti::paretoFront::parameters.
| lti::locationSearchEvaluation::parameters::parameters | ( | const parameters & | other | ) |
Copy constructor.
| other | the parameters object to be copied |
Reimplemented from lti::paretoFront::parameters.
| lti::locationSearchEvaluation::parameters::~parameters | ( | ) | [virtual] |
Destructor.
Reimplemented from lti::paretoFront::parameters.
| virtual functor::parameters* lti::locationSearchEvaluation::parameters::clone | ( | ) | const [virtual] |
Returns a pointer to a clone of the parameters.
Reimplemented from lti::paretoFront::parameters.
| parameters& lti::locationSearchEvaluation::parameters::copy | ( | const parameters & | other | ) |
Copy the contents of a parameters object.
| other | the parameters object to be copied |
Reimplemented from lti::paretoFront::parameters.
| const char* lti::locationSearchEvaluation::parameters::getTypeName | ( | ) | const [virtual] |
Returns name of this type.
Reimplemented from lti::paretoFront::parameters.
| parameters& lti::locationSearchEvaluation::parameters::operator= | ( | const parameters & | other | ) |
Copy the contents of a parameters object.
| other | the parameters object to be copied |
Reimplemented from lti::paretoFront::parameters.
| virtual bool lti::locationSearchEvaluation::parameters::read | ( | ioHandler & | handler, | |
| const bool & | complete = true | |||
| ) | [virtual] |
Read the parameters from the given ioHandler.
| handler | the ioHandler to be used | |
| complete | if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written. |
Reimplemented from lti::paretoFront::parameters.
| virtual bool lti::locationSearchEvaluation::parameters::write | ( | ioHandler & | handler, | |
| const bool & | complete = true | |||
| ) | const [virtual] |
Write the parameters in the given ioHandler.
| handler | the ioHandler to be used | |
| complete | if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written. |
Reimplemented from lti::paretoFront::parameters.
Angular tolerance.
Two locations, which coincide in position and scale, match together if the angular difference is smaller than the given angle.
This must be given in radians, but if you give a value greater than 2*Pi, it will be assumed to be in degrees.
Default value: lti::degToRad(10), i.e. 10 degrees in radians.
First angle.
This must be given in radians, but if you give a value greater than 2*Pi, it will be assumed to be in degrees.
Default value 0
Name of a file containing all images to be analyzed.
Default value: "images.txt"
Last rotation angle.
This must be given in radians, but if you give a value greater than 2*Pi, it will be assumed to be in degrees.
Default value: 2*Pi
Last scaling of the image will be an upsampling by a factor of 2.
Default value: 2
Locations' reciprocal.
This is the inverse of the number of location (1/number of locations). It is often better to search of parameterizations that produce a low number of locations. The used value will be 1/(1+#locs) to avoid divisions by zero.
Default value: false
Values for all parameters of the pyramidLocationSearch functor that will be used as minima.
Default value: numLevels 30 upsampleFirstLevel 3 pyramidParameters::factor pow(0.5,1.0/8.0) pyramidParameters::gaussian true pyramidParameters::interpolatorType BiquadraticInterpolator interpolateMaxima true smoothingGaussianVariance 5 spatialMaximumNeighborhoodSize 7 peakSelectionMode DoG doGLevelDistance 4 doGKernelVariance 4 saliencyThreshold 0.99 edgenessThreshold 10 orientationWindowRadius = 5
Values for all parameters of the pyramidLocationSearch functor that will be used as minima.
Default value: numLevels 4 upsampleFirstLevel 0 pyramidParameters::factor 0.5 pyramidParameters::gaussian false pyramidParameters::interpolatorType BilinearInterpolator interpolateMaxima false smoothingGaussianVariance 0 spatialMaximumNeighborhoodSize 3 peakSelectionMode GradientMagnitude doGLevelDistance 1 doGKernelVariance 1 saliencyThreshold 0 edgenessThreshold 2 orientationWindowRadius = 2
Total number of locations detected per image.
Default value: false
Percentage of generated levels with locations.
Useful to detect how many levels are really necessary.
Default value: false
Tolerance for position deviation.
Between two candidate matching locations, the match will be accepted only if the distance between both locations does not exceed the given tolerance value, which must be always positive.
Default value: 1.5f
Mask posfix.
For each image file in images, a manual segmented mask can be used to ignore those locations outside the objects of interest.
The filename of the masks will be assumed to be the same image name with the given postfix. For example, if a image is called "test.png" and the postfix is "-preseg", then the mask will be assumed to be "test-preseg.png".
Default value: "_premask"
Tolerance for scale deviation.
Between two candidate matching locations, the match will be accepted only if the ratio between scale of both locations does not goes beneath the given tolerance value, which must be always smaller than one.
Default value: 1/sqrt(2)
Additive angle change.
The interval from firstAngle to lastAngle will be divided in subintervals with a width stepAngle.
This must be given in radians, but if you give a value greater than 2*Pi, it will be assumed to be in degrees.
Default value: lti::degToRad(10), i.e. 10 degrees in radians.
Mean time required to extract the locations.
Default value: true