Class cv::saliency::ObjectnessBING#

Objectness algorithms based on [3] [3] Cheng, Ming-Ming, et al. "[61]: Binarized normed gradients for objectness estimation at 300fps." IEEE CVPR. 2014. View details

#include <opencv2/saliency/saliencySpecializedClasses.hpp>

Collaboration diagram for cv::saliency::ObjectnessBING:

Public Member Functions#

Public Member Functions inherited from cv::saliency::Saliency

Return	Name	Description
	`~Saliency()`	Destructor.
`bool`	`computeSaliency(` `InputArray image,` `OutputArray saliencyMap )`	Compute the saliency.

Public Member Functions inherited from cv::Algorithm

Return	Name	Description
	`Algorithm()`
	`~Algorithm()`
`void`	`clear()`	Clears the algorithm state.
`bool`	`empty()`	Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read.
`String`	`getDefaultName()`
`void`	`read(const FileNode & fn)`	Reads algorithm parameters from a file storage.
`void`	`save(const String & filename)`
`void`	`write(` `const Ptr< FileStorage > & fs,` `const String & name = String() )`
`void`	`write(FileStorage & fs)`	Stores algorithm parameters in a file storage.
`void`	`write(` `FileStorage & fs,` `const String & name )`

Static Public Member Functions#

Static Public Member Functions inherited from cv::Algorithm

Return	Name	Description
`static Ptr< _Tp >`	`load(` `const String & filename,` `const String & objname = String() )`	Loads algorithm from the file.
`static Ptr< _Tp >`	`loadFromString(` `const String & strModel,` `const String & objname = String() )`	Loads algorithm from a String.
`static Ptr< _Tp >`	`read(const FileNode & fn)`	Reads algorithm from the file node.

Additional Inherited Members#

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 BING

Member Enumeration Documentation#

enum ObjectnessBING

MAXBGR

HSV

G

Constructor & Destructor Documentation#

ObjectnessBING()#

cv::saliency::ObjectnessBING::ObjectnessBING()

~ObjectnessBING()#

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

Member Function Documentation#

computeSaliency()#

bool cv::saliency::ObjectnessBING::computeSaliency(
InputArray image,
OutputArray saliencyMap )

Python:

cv.saliency.ObjectnessBING.computeSaliency(image[, saliencyMap]) -> retval, saliencyMap

Here is the call graph for this function:

getBase()#

double cv::saliency::ObjectnessBING::getBase()

Python:

cv.saliency.ObjectnessBING.getBase() -> retval

getNSS()#

int cv::saliency::ObjectnessBING::getNSS()

Python:

cv.saliency.ObjectnessBING.getNSS() -> retval

getobjectnessValues()#

std::vector< float > cv::saliency::ObjectnessBING::getobjectnessValues()

Python:

cv.saliency.ObjectnessBING.getobjectnessValues() -> retval

Return the list of the rectangles’ objectness value,.

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

getW()#

int cv::saliency::ObjectnessBING::getW()

Python:

cv.saliency.ObjectnessBING.getW() -> retval

setBase()#

void cv::saliency::ObjectnessBING::setBase(double val)

Python:

cv.saliency.ObjectnessBING.setBase(val)

setBBResDir()#

void cv::saliency::ObjectnessBING::setBBResDir(const String & resultsDir)

Python:

cv.saliency.ObjectnessBING.setBBResDir(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

resultsDir — results’ folder path

setNSS()#

void cv::saliency::ObjectnessBING::setNSS(int val)

Python:

cv.saliency.ObjectnessBING.setNSS(val)

setTrainingPath()#

void cv::saliency::ObjectnessBING::setTrainingPath(const String & trainingPath)

Python:

cv.saliency.ObjectnessBING.setTrainingPath(trainingPath)

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

Parameters

trainingPath — trained model path

setW()#

void cv::saliency::ObjectnessBING::setW(int val)

Python:

cv.saliency.ObjectnessBING.setW(val)

create()#

static Ptr< ObjectnessBING > cv::saliency::ObjectnessBING::create()

Python:

cv.saliency.ObjectnessBING.create() -> retval

cv.saliency.ObjectnessBING_create() -> retval

computeSaliencyImpl()#

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

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

Parameters

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

Here is the call graph for this function:

bgrMaxDist()#

static int cv::saliency::ObjectnessBING::bgrMaxDist(
const Vec3b & u,
const Vec3b & v )

gradientGray()#

static void cv::saliency::ObjectnessBING::gradientGray(
Mat & bgr3u,
Mat & mag1u )

gradientHSV()#

static void cv::saliency::ObjectnessBING::gradientHSV(
Mat & bgr3u,
Mat & mag1u )

gradientRGB()#

static void cv::saliency::ObjectnessBING::gradientRGB(
Mat & bgr3u,
Mat & mag1u )

gradientXY()#

static void cv::saliency::ObjectnessBING::gradientXY(
Mat & x1i,
Mat & y1i,
Mat & mag1u )

LoG()#

static float cv::saliency::ObjectnessBING::LoG(
float x,
float y,
float delta )

matRead()#

static bool cv::saliency::ObjectnessBING::matRead(
const std::string & filename,
Mat & M )

nonMaxSup()#

static void cv::saliency::ObjectnessBING::nonMaxSup(
Mat & matchCost1f,
ValStructVec< float, Point > & matchCost,
int NSS = 1,
int maxPoint = 50,
bool fast = true )

vecDist3b()#

static int cv::saliency::ObjectnessBING::vecDist3b(
const Vec3b & u,
const Vec3b & v )

filtersLoaded()#

bool cv::saliency::ObjectnessBING::filtersLoaded()

getObjBndBoxes()#

void cv::saliency::ObjectnessBING::getObjBndBoxes(
Mat & img3u,
ValStructVec< float, Vec4i > & valBoxes,
int numDetPerSize = 120 )

getObjBndBoxesForSingleImage()#

void cv::saliency::ObjectnessBING::getObjBndBoxesForSingleImage(
Mat img,
ValStructVec< float, Vec4i > & boxes,
int numDetPerSize )

gradientMag()#

void cv::saliency::ObjectnessBING::gradientMag(
Mat & imgBGR3u,
Mat & mag1u )

loadTrainedModel()#

int cv::saliency::ObjectnessBING::loadTrainedModel()

predictBBoxSI()#

void cv::saliency::ObjectnessBING::predictBBoxSI(
Mat & mag3u,
ValStructVec< float, Vec4i > & valBoxes,
std::vector< int > & sz,
int NUM_WIN_PSZ = 100,
bool fast = true )

predictBBoxSII()#

void cv::saliency::ObjectnessBING::predictBBoxSII(
ValStructVec< float, Vec4i > & valBoxes,
const std::vector< int > & sz )

setColorSpace()#

void cv::saliency::ObjectnessBING::setColorSpace(int clr = MAXBGR)

Member Data Documentation#

_base#

double cv::saliency::ObjectnessBING::_base

_bbResDir#

std::string cv::saliency::ObjectnessBING::_bbResDir

_Clr#

int cv::saliency::ObjectnessBING::_Clr

_logBase#

double cv::saliency::ObjectnessBING::_logBase

_maxT#

int cv::saliency::ObjectnessBING::_maxT

_minT#

int cv::saliency::ObjectnessBING::_minT

_modelName#

std::string cv::saliency::ObjectnessBING::_modelName

_NSS#

int cv::saliency::ObjectnessBING::_NSS

_numT#

int cv::saliency::ObjectnessBING::_numT

_resultsDir#

std::string cv::saliency::ObjectnessBING::_resultsDir

_svmFilter#

Mat cv::saliency::ObjectnessBING::_svmFilter

_svmReW1f#

Mat cv::saliency::ObjectnessBING::_svmReW1f

_svmSzIdxs#

std::vector< int > cv::saliency::ObjectnessBING::_svmSzIdxs

_tigF#

FilterTIG cv::saliency::ObjectnessBING::_tigF

_trainingPath#

std::string cv::saliency::ObjectnessBING::_trainingPath

_W#

int cv::saliency::ObjectnessBING::_W

objectnessValues#

std::vector< float > cv::saliency::ObjectnessBING::objectnessValues

_clrName#

static const char * cv::saliency::ObjectnessBING::_clrName

Source file#

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

opencv2/saliency/saliencySpecializedClasses.hpp