OpenCV  3.0.0-rc1
Open Source Computer Vision
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Properties Friends Macros Groups Pages
Classes | Public Member Functions | Protected Member Functions | List of all members
cv::saliency::ObjectnessBING Class Reference

Objectness algorithms based on [3] [3] Cheng, Ming-Ming, et al. "BING: Binarized normed gradients for objectness estimation at 300fps." IEEE CVPR. 2014. More...

#include "saliencySpecializedClasses.hpp"

Inheritance diagram for cv::saliency::ObjectnessBING:
cv::saliency::Objectness cv::saliency::Saliency cv::Algorithm

Public Member Functions

 ObjectnessBING ()
 
virtual ~ObjectnessBING ()
 
double getBase () const
 
int getNSS () const
 
std::vector< float > getobjectnessValues ()
 Return the list of the rectangles' objectness value,. More...
 
int getW () const
 
void read ()
 
void setBase (double val)
 
void setBBResDir (std::string resultsDir)
 This is a utility function that allows to set an arbitrary path in which the algorithm will save the optional results. More...
 
void setNSS (int val)
 
void setTrainingPath (std::string trainingPath)
 This is a utility function that allows to set the correct path from which the algorithm will load the trained model. More...
 
void setW (int val)
 
void write () const
 
- Public Member Functions inherited from cv::saliency::Saliency
virtual ~Saliency ()
 Destructor. More...
 
bool computeSaliency (const InputArray image, OutputArray saliencyMap)
 Compute the saliency. More...
 
String getClassName () const
 Get the name of the specific saliency type. More...
 
- Public Member Functions inherited from cv::Algorithm
 Algorithm ()
 
virtual ~Algorithm ()
 
virtual void clear ()
 Clears the algorithm state. More...
 
virtual bool empty () const
 Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...
 
virtual String getDefaultName () const
 
virtual void read (const FileNode &fn)
 Reads algorithm parameters from a file storage. More...
 
virtual void save (const String &filename) const
 
virtual void write (FileStorage &fs) const
 Stores algorithm parameters in a file storage. More...
 

Protected Member Functions

bool computeSaliencyImpl (const InputArray image, OutputArray objectnessBoundingBox)
 Performs all the operations and calls all internal functions necessary for the accomplishment of the Binarized normed gradients algorithm. More...
 

Additional Inherited Members

- Static Public Member Functions inherited from cv::saliency::Saliency
static Ptr< Saliencycreate (const String &saliencyType)
 Create Saliency by saliency type. More...
 
- Static Public Member Functions inherited from cv::Algorithm
template<typename _Tp >
static Ptr< _Tp > load (const String &filename, const String &objname=String())
 Loads algorithm from the file. More...
 
template<typename _Tp >
static Ptr< _Tp > loadFromString (const String &strModel, const String &objname=String())
 Loads algorithm from a String. More...
 
template<typename _Tp >
static Ptr< _Tp > read (const FileNode &fn)
 Reads algorithm from the file node. More...
 
- Protected Attributes inherited from cv::saliency::Saliency
String className
 

Detailed Description

Objectness algorithms based on [3] [3] Cheng, Ming-Ming, et al. "BING: Binarized normed gradients for objectness estimation at 300fps." IEEE CVPR. 2014.

the Binarized normed gradients algorithm from [26]

Constructor & Destructor Documentation

cv::saliency::ObjectnessBING::ObjectnessBING ( )
virtual cv::saliency::ObjectnessBING::~ObjectnessBING ( )
virtual

Member Function Documentation

bool cv::saliency::ObjectnessBING::computeSaliencyImpl ( const InputArray  image,
OutputArray  objectnessBoundingBox 
)
protectedvirtual

Performs all the operations and calls all internal functions necessary for the accomplishment of the Binarized normed gradients algorithm.

Parameters
imageinput image. According to the needs of this specialized algorithm, the param image is a single Mat
objectnessBoundingBoxobjectness Bounding Box vector. According to the result given by this specialized algorithm, the objectnessBoundingBox is a vector<Vec4i>. Each bounding box is represented by a Vec4i for (minX, minY, maxX, maxY).

Implements cv::saliency::Objectness.

double cv::saliency::ObjectnessBING::getBase ( ) const
inline
int cv::saliency::ObjectnessBING::getNSS ( ) const
inline
std::vector<float> cv::saliency::ObjectnessBING::getobjectnessValues ( )

Return the list of the rectangles' objectness value,.

in the same order as the vector<Vec4i> objectnessBoundingBox returned by the algorithm (in computeSaliencyImpl function). The bigger value these scores are, it is more likely to be an object window.

int cv::saliency::ObjectnessBING::getW ( ) const
inline
void cv::saliency::ObjectnessBING::read ( )
void cv::saliency::ObjectnessBING::setBase ( double  val)
inline
void cv::saliency::ObjectnessBING::setBBResDir ( std::string  resultsDir)

This is a utility function that allows to set an arbitrary path in which the algorithm will save the optional results.

(ie writing on file the total number and the list of rectangles returned by objectess, one for each row).

Parameters
resultsDirresults' folder path
void cv::saliency::ObjectnessBING::setNSS ( int  val)
inline
void cv::saliency::ObjectnessBING::setTrainingPath ( std::string  trainingPath)

This is a utility function that allows to set the correct path from which the algorithm will load the trained model.

Parameters
trainingPathtrained model path
void cv::saliency::ObjectnessBING::setW ( int  val)
inline
void cv::saliency::ObjectnessBING::write ( ) const

The documentation for this class was generated from the following file: