OpenCV  4.5.2
Open Source Computer Vision
Namespaces | Classes | Enumerations | Functions

Namespaces

 calib3d
 
 compound
 
 core
 
 cpu
 
 detail
 
 fluid
 
 ie
 
 imgproc
 
 nn
 
 ocl
 
 onnx
 
 own
 
 plaidml
 
 python
 
 render
 
 s11n
 
 streaming
 
 video
 
 wip
 

Classes

class  GBackend
 
struct  Generic
 Special network type. More...
 
class  GFunctor
 
class  GKernelPackage
 A container class for heterogeneous kernel implementation collections and graph transformations. More...
 
struct  GNetPackage
 A container class for network configurations. Similar to GKernelPackage.Use cv::gapi::networks() to construct this object. More...
 
struct  GNetParam
 
struct  KalmanParams
 Structure for the Kalman filter's initialization parameters. More...
 
struct  use_only
 cv::use_only() is a special combinator which hints G-API to use only kernels specified in cv::GComputation::compile() (and not to extend kernels available by default with that package). More...
 

Enumerations

enum  StereoOutputFormat {
  StereoOutputFormat::DEPTH_FLOAT16,
  StereoOutputFormat::DEPTH_FLOAT32,
  StereoOutputFormat::DISPARITY_FIXED16_11_5,
  StereoOutputFormat::DISPARITY_FIXED16_12_4
}
 

Functions

GMat absDiff (const GMat &src1, const GMat &src2)
 Calculates the per-element absolute difference between two matrices. More...
 
GMat absDiffC (const GMat &src, const GScalar &c)
 Calculates absolute value of matrix elements. More...
 
GMat add (const GMat &src1, const GMat &src2, int ddepth=-1)
 Calculates the per-element sum of two matrices. More...
 
GMat addC (const GMat &src1, const GScalar &c, int ddepth=-1)
 Calculates the per-element sum of matrix and given scalar. More...
 
GMat addC (const GScalar &c, const GMat &src1, int ddepth=-1)
 
GMat addWeighted (const GMat &src1, double alpha, const GMat &src2, double beta, double gamma, int ddepth=-1)
 Calculates the weighted sum of two matrices. More...
 
GMat BackgroundSubtractor (const GMat &src, const cv::gapi::video::BackgroundSubtractorParams &bsParams)
 Gaussian Mixture-based or K-nearest neighbours-based Background/Foreground Segmentation Algorithm. The operation generates a foreground mask. More...
 
GMat BayerGR2RGB (const GMat &src_gr)
 Converts an image from BayerGR color space to RGB. The function converts an input image from BayerGR color space to RGB. The conventional ranges for G, R, and B channel values are 0 to 255. More...
 
GMat BGR2Gray (const GMat &src)
 Converts an image from BGR color space to gray-scaled. More...
 
GMat BGR2I420 (const GMat &src)
 Converts an image from BGR color space to I420 color space. More...
 
GMat BGR2LUV (const GMat &src)
 Converts an image from BGR color space to LUV color space. More...
 
GMat BGR2RGB (const GMat &src)
 Converts an image from BGR color space to RGB color space. More...
 
GMat BGR2YUV (const GMat &src)
 Converts an image from BGR color space to YUV color space. More...
 
GMat bilateralFilter (const GMat &src, int d, double sigmaColor, double sigmaSpace, int borderType=BORDER_DEFAULT)
 Applies the bilateral filter to an image. More...
 
cv::GRunArgsP bind (cv::GRunArgs &results)
 
cv::GRunArg bind (cv::GRunArgP &out)
 
GMat bitwise_and (const GMat &src1, const GMat &src2)
 computes bitwise conjunction of the two matrixes (src1 & src2) Calculates the per-element bit-wise logical conjunction of two matrices of the same size. More...
 
GMat bitwise_and (const GMat &src1, const GScalar &src2)
 
GMat bitwise_not (const GMat &src)
 Inverts every bit of an array. More...
 
GMat bitwise_or (const GMat &src1, const GMat &src2)
 computes bitwise disjunction of the two matrixes (src1 | src2) Calculates the per-element bit-wise logical disjunction of two matrices of the same size. More...
 
GMat bitwise_or (const GMat &src1, const GScalar &src2)
 
GMat bitwise_xor (const GMat &src1, const GMat &src2)
 computes bitwise logical "exclusive or" of the two matrixes (src1 ^ src2) Calculates the per-element bit-wise logical "exclusive or" of two matrices of the same size. More...
 
GMat bitwise_xor (const GMat &src1, const GScalar &src2)
 
GMat blur (const GMat &src, const Size &ksize, const Point &anchor=Point(-1,-1), int borderType=BORDER_DEFAULT, const Scalar &borderValue=Scalar(0))
 Blurs an image using the normalized box filter. More...
 
GOpaque< RectboundingRect (const GMat &src)
 Calculates the up-right bounding rectangle of a point set or non-zero pixels of gray-scale image. More...
 
GOpaque< RectboundingRect (const GArray< Point2i > &src)
 
GOpaque< RectboundingRect (const GArray< Point2f > &src)
 
GMat boxFilter (const GMat &src, int dtype, const Size &ksize, const Point &anchor=Point(-1,-1), bool normalize=true, int borderType=BORDER_DEFAULT, const Scalar &borderValue=Scalar(0))
 Blurs an image using the box filter. More...
 
std::tuple< GArray< GMat >, GScalarbuildOpticalFlowPyramid (const GMat &img, const Size &winSize, const GScalar &maxLevel, bool withDerivatives=true, int pyrBorder=BORDER_REFLECT_101, int derivBorder=BORDER_CONSTANT, bool tryReuseInputImage=true)
 Constructs the image pyramid which can be passed to calcOpticalFlowPyrLK. More...
 
std::tuple< GArray< Point2f >, GArray< uchar >, GArray< float > > calcOpticalFlowPyrLK (const GMat &prevImg, const GMat &nextImg, const GArray< Point2f > &prevPts, const GArray< Point2f > &predPts, const Size &winSize=Size(21, 21), const GScalar &maxLevel=3, const TermCriteria &criteria=TermCriteria(TermCriteria::COUNT|TermCriteria::EPS, 30, 0.01), int flags=0, double minEigThresh=1e-4)
 Calculates an optical flow for a sparse feature set using the iterative Lucas-Kanade method with pyramids. More...
 
std::tuple< GArray< Point2f >, GArray< uchar >, GArray< float > > calcOpticalFlowPyrLK (const GArray< GMat > &prevPyr, const GArray< GMat > &nextPyr, const GArray< Point2f > &prevPts, const GArray< Point2f > &predPts, const Size &winSize=Size(21, 21), const GScalar &maxLevel=3, const TermCriteria &criteria=TermCriteria(TermCriteria::COUNT|TermCriteria::EPS, 30, 0.01), int flags=0, double minEigThresh=1e-4)
 
GMat Canny (const GMat &image, double threshold1, double threshold2, int apertureSize=3, bool L2gradient=false)
 Finds edges in an image using the Canny algorithm. More...
 
std::tuple< GMat, GMatcartToPolar (const GMat &x, const GMat &y, bool angleInDegrees=false)
 Calculates the magnitude and angle of 2D vectors. More...
 
GMat cmpEQ (const GMat &src1, const GMat &src2)
 Performs the per-element comparison of two matrices checking if elements from first matrix are equal to elements in second. More...
 
GMat cmpEQ (const GMat &src1, const GScalar &src2)
 
GMat cmpGE (const GMat &src1, const GMat &src2)
 Performs the per-element comparison of two matrices checking if elements from first matrix are greater or equal compare to elements in second. More...
 
GMat cmpGE (const GMat &src1, const GScalar &src2)
 
GMat cmpGT (const GMat &src1, const GMat &src2)
 Performs the per-element comparison of two matrices checking if elements from first matrix are greater compare to elements in second. More...
 
GMat cmpGT (const GMat &src1, const GScalar &src2)
 
GMat cmpLE (const GMat &src1, const GMat &src2)
 Performs the per-element comparison of two matrices checking if elements from first matrix are less or equal compare to elements in second. More...
 
GMat cmpLE (const GMat &src1, const GScalar &src2)
 
GMat cmpLT (const GMat &src1, const GMat &src2)
 Performs the per-element comparison of two matrices checking if elements from first matrix are less than elements in second. More...
 
GMat cmpLT (const GMat &src1, const GScalar &src2)
 
GMat cmpNE (const GMat &src1, const GMat &src2)
 Performs the per-element comparison of two matrices checking if elements from first matrix are not equal to elements in second. More...
 
GMat cmpNE (const GMat &src1, const GScalar &src2)
 
GKernelPackage combine (const GKernelPackage &lhs, const GKernelPackage &rhs)
 
template<typename... Ps>
GKernelPackage combine (const GKernelPackage &a, const GKernelPackage &b, Ps &&... rest)
 Combines multiple G-API kernel packages into one. More...
 
GMat concatHor (const GMat &src1, const GMat &src2)
 Applies horizontal concatenation to given matrices. More...
 
GMat concatHor (const std::vector< GMat > &v)
 
GMat concatVert (const GMat &src1, const GMat &src2)
 Applies vertical concatenation to given matrices. More...
 
GMat concatVert (const std::vector< GMat > &v)
 
GMat convertTo (const GMat &src, int rdepth, double alpha=1, double beta=0)
 Converts a matrix to another data depth with optional scaling. More...
 
GMat copy (const GMat &in)
 Makes a copy of the input image. Note that this copy may be not real (no actual data copied). Use this function to maintain graph contracts, e.g when graph's input needs to be passed directly to output, like in Streaming mode. More...
 
GFrame copy (const GFrame &in)
 Makes a copy of the input frame. Note that this copy may be not real (no actual data copied). Use this function to maintain graph contracts, e.g when graph's input needs to be passed directly to output, like in Streaming mode. More...
 
GOpaque< int > countNonZero (const GMat &src)
 Counts non-zero array elements. More...
 
GMat crop (const GMat &src, const Rect &rect)
 Crops a 2D matrix. More...
 
template<typename T >
static T deserialize (const std::vector< char > &p)
 
template<>
cv::GComputation deserialize (const std::vector< char > &p)
 
template<>
cv::GMetaArgs deserialize (const std::vector< char > &p)
 
template<>
cv::GRunArgs deserialize (const std::vector< char > &p)
 
template<>
std::vector< std::string > deserialize (const std::vector< char > &p)
 
template<typename T , typename... Types>
std::enable_if< std::is_same< T, GCompileArgs >::value, GCompileArgs >::type deserialize (const std::vector< char > &p)
 
template<typename T , typename RMatAdapterType >
std::enable_if< std::is_same< T, GRunArgs >::value, GRunArgs >::type deserialize (const std::vector< char > &p)
 
GMat dilate (const GMat &src, const Mat &kernel, const Point &anchor=Point(-1,-1), int iterations=1, int borderType=BORDER_CONSTANT, const Scalar &borderValue=morphologyDefaultBorderValue())
 Dilates an image by using a specific structuring element. More...
 
GMat dilate3x3 (const GMat &src, int iterations=1, int borderType=BORDER_CONSTANT, const Scalar &borderValue=morphologyDefaultBorderValue())
 Dilates an image by using 3 by 3 rectangular structuring element. More...
 
GMat div (const GMat &src1, const GMat &src2, double scale, int ddepth=-1)
 Performs per-element division of two matrices. More...
 
GMat divC (const GMat &src, const GScalar &divisor, double scale, int ddepth=-1)
 Divides matrix by scalar. More...
 
GMat divRC (const GScalar &divident, const GMat &src, double scale, int ddepth=-1)
 Divides scalar by matrix. More...
 
GMat equalizeHist (const GMat &src)
 
GMat erode (const GMat &src, const Mat &kernel, const Point &anchor=Point(-1,-1), int iterations=1, int borderType=BORDER_CONSTANT, const Scalar &borderValue=morphologyDefaultBorderValue())
 Erodes an image by using a specific structuring element. More...
 
GMat erode3x3 (const GMat &src, int iterations=1, int borderType=BORDER_CONSTANT, const Scalar &borderValue=morphologyDefaultBorderValue())
 Erodes an image by using 3 by 3 rectangular structuring element. More...
 
GMat filter2D (const GMat &src, int ddepth, const Mat &kernel, const Point &anchor=Point(-1,-1), const Scalar &delta=Scalar(0), int borderType=BORDER_DEFAULT, const Scalar &borderValue=Scalar(0))
 Convolves an image with the kernel. More...
 
GArray< GArray< Point > > findContours (const GMat &src, const RetrievalModes mode, const ContourApproximationModes method, const GOpaque< Point > &offset)
 Finds contours in a binary image. More...
 
GArray< GArray< Point > > findContours (const GMat &src, const RetrievalModes mode, const ContourApproximationModes method)
 
std::tuple< GArray< GArray< Point > >, GArray< Vec4i > > findContoursH (const GMat &src, const RetrievalModes mode, const ContourApproximationModes method, const GOpaque< Point > &offset)
 Finds contours and their hierarchy in a binary image. More...
 
std::tuple< GArray< GArray< Point > >, GArray< Vec4i > > findContoursH (const GMat &src, const RetrievalModes mode, const ContourApproximationModes method)
 
GOpaque< Vec4ffitLine2D (const GMat &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 Fits a line to a 2D point set. More...
 
GOpaque< Vec4ffitLine2D (const GArray< Point2i > &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 
GOpaque< Vec4ffitLine2D (const GArray< Point2f > &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 
GOpaque< Vec4ffitLine2D (const GArray< Point2d > &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 
GOpaque< Vec6ffitLine3D (const GMat &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 Fits a line to a 3D point set. More...
 
GOpaque< Vec6ffitLine3D (const GArray< Point3i > &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 
GOpaque< Vec6ffitLine3D (const GArray< Point3f > &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 
GOpaque< Vec6ffitLine3D (const GArray< Point3d > &src, const DistanceTypes distType, const double param=0., const double reps=0., const double aeps=0.)
 
GMat flip (const GMat &src, int flipCode)
 Flips a 2D matrix around vertical, horizontal, or both axes. More...
 
GMat gaussianBlur (const GMat &src, const Size &ksize, double sigmaX, double sigmaY=0, int borderType=BORDER_DEFAULT, const Scalar &borderValue=Scalar(0))
 Blurs an image using a Gaussian filter. More...
 
template<typename T >
cv::util::optional< T > getCompileArg (const cv::GCompileArgs &args)
 Retrieves particular compilation argument by its type from cv::GCompileArgs. More...
 
GArray< Point2fgoodFeaturesToTrack (const GMat &image, int maxCorners, double qualityLevel, double minDistance, const Mat &mask=Mat(), int blockSize=3, bool useHarrisDetector=false, double k=0.04)
 Determines strong corners on an image. More...
 
GMat I4202BGR (const GMat &src)
 Converts an image from I420 color space to BGR color space. More...
 
GMat I4202RGB (const GMat &src)
 Converts an image from I420 color space to BGR color space. More...
 
template<typename Net , typename T >
Net::Result infer (cv::GOpaque< cv::Rect > roi, T in)
 Calculates response for the specified network (template parameter) for the specified region in the source image. Currently expects a single-input network only. More...
 
template<typename Net , typename... Args>
Net::ResultL infer (cv::GArray< cv::Rect > roi, Args &&... args)
 Calculates responses for the specified network (template parameter) for every region in the source image. More...
 
template<typename Net , typename... Args>
Net::Result infer (Args &&... args)
 Calculates response for the specified network (template parameter) given the input data. More...
 
template<typename T = Generic>
cv::GInferOutputs infer (const std::string &tag, const cv::GInferInputs &inputs)
 Calculates response for generic network. More...
 
template<typename T = Generic>
cv::GInferOutputs infer (const std::string &tag, const cv::GOpaque< cv::Rect > &roi, const cv::GInferInputs &inputs)
 Calculates response for the generic network for the specified region in the source image. Currently expects a single-input network only. More...
 
template<typename T = Generic>
cv::GInferListOutputs infer (const std::string &tag, const cv::GArray< cv::Rect > &rois, const cv::GInferInputs &inputs)
 Calculates responses for the specified network for every region in the source image. More...
 
template<typename Net , typename T , typename... Args>
Net::ResultL infer2 (T image, cv::GArray< Args >... args)
 Calculates responses for the specified network (template parameter) for every region in the source image, extended version. More...
 
template<typename T = Generic, typename Input >
std::enable_if< cv::detail::accepted_infer_types< Input >::value, cv::GInferListOutputs >::type infer2 (const std::string &tag, const Input &in, const cv::GInferListInputs &inputs)
 Calculates responses for the specified network for every region in the source image, extended version. More...
 
GMat inRange (const GMat &src, const GScalar &threshLow, const GScalar &threshUp)
 Applies a range-level threshold to each matrix element. More...
 
std::tuple< GMat, GMatintegral (const GMat &src, int sdepth=-1, int sqdepth=-1)
 Calculates the integral of an image. More...
 
void island (const std::string &name, GProtoInputArgs &&ins, GProtoOutputArgs &&outs)
 Define an tagged island (subgraph) within a computation. More...
 
GMat KalmanFilter (const GMat &measurement, const GOpaque< bool > &haveMeasurement, const GMat &control, const cv::gapi::KalmanParams &kfParams)
 Standard Kalman filter algorithm http://en.wikipedia.org/wiki/Kalman_filter. More...
 
GMat KalmanFilter (const GMat &measurement, const GOpaque< bool > &haveMeasurement, const cv::gapi::KalmanParams &kfParams)
 
template<typename... KK>
GKernelPackage kernels ()
 Create a kernel package object containing kernels and transformations specified in variadic template argument. More...
 
template<typename... FF>
GKernelPackage kernels (FF &... functors)
 
std::tuple< GOpaque< double >, GMat, GMatkmeans (const GMat &data, const int K, const GMat &bestLabels, const TermCriteria &criteria, const int attempts, const KmeansFlags flags)
 Finds centers of clusters and groups input samples around the clusters. More...
 
std::tuple< GOpaque< double >, GMat, GMatkmeans (const GMat &data, const int K, const TermCriteria &criteria, const int attempts, const KmeansFlags flags)
 
std::tuple< GOpaque< double >, GArray< int >, GArray< Point2f > > kmeans (const GArray< Point2f > &data, const int K, const GArray< int > &bestLabels, const TermCriteria &criteria, const int attempts, const KmeansFlags flags)
 
std::tuple< GOpaque< double >, GArray< int >, GArray< Point3f > > kmeans (const GArray< Point3f > &data, const int K, const GArray< int > &bestLabels, const TermCriteria &criteria, const int attempts, const KmeansFlags flags)
 
GMat Laplacian (const GMat &src, int ddepth, int ksize=1, double scale=1, double delta=0, int borderType=BORDER_DEFAULT)
 Calculates the Laplacian of an image. More...
 
GMat LUT (const GMat &src, const Mat &lut)
 Performs a look-up table transform of a matrix. More...
 
GMat LUV2BGR (const GMat &src)
 Converts an image from LUV color space to BGR color space. More...
 
GMat mask (const GMat &src, const GMat &mask)
 Applies a mask to a matrix. More...
 
GMat max (const GMat &src1, const GMat &src2)
 Calculates per-element maximum of two matrices. More...
 
GScalar mean (const GMat &src)
 Calculates an average (mean) of matrix elements. More...
 
GMat medianBlur (const GMat &src, int ksize)
 Blurs an image using the median filter. More...
 
GMat merge3 (const GMat &src1, const GMat &src2, const GMat &src3)
 Creates one 3-channel matrix out of 3 single-channel ones. More...
 
GMat merge4 (const GMat &src1, const GMat &src2, const GMat &src3, const GMat &src4)
 Creates one 4-channel matrix out of 4 single-channel ones. More...
 
GMat min (const GMat &src1, const GMat &src2)
 Calculates per-element minimum of two matrices. More...
 
GMat morphologyEx (const GMat &src, const MorphTypes op, const Mat &kernel, const Point &anchor=Point(-1,-1), const int iterations=1, const BorderTypes borderType=BORDER_CONSTANT, const Scalar &borderValue=morphologyDefaultBorderValue())
 Performs advanced morphological transformations. More...
 
GMat mul (const GMat &src1, const GMat &src2, double scale=1.0, int ddepth=-1)
 Calculates the per-element scaled product of two matrices. More...
 
GMat mulC (const GMat &src, double multiplier, int ddepth=-1)
 Multiplies matrix by scalar. More...
 
GMat mulC (const GMat &src, const GScalar &multiplier, int ddepth=-1)
 
GMat mulC (const GScalar &multiplier, const GMat &src, int ddepth=-1)
 
template<typename... Args>
cv::gapi::GNetPackage networks (Args &&... args)
 
GMat normalize (const GMat &src, double alpha, double beta, int norm_type, int ddepth=-1)
 Normalizes the norm or value range of an array. More...
 
GScalar normInf (const GMat &src)
 Calculates the absolute infinite norm of a matrix. More...
 
GScalar normL1 (const GMat &src)
 Calculates the absolute L1 norm of a matrix. More...
 
GScalar normL2 (const GMat &src)
 Calculates the absolute L2 norm of a matrix. More...
 
GMat NV12toBGR (const GMat &src_y, const GMat &src_uv)
 Converts an image from NV12 (YUV420p) color space to BGR. The function converts an input image from NV12 color space to RGB. The conventional ranges for Y, U, and V channel values are 0 to 255. More...
 
GMatP NV12toBGRp (const GMat &src_y, const GMat &src_uv)
 Converts an image from NV12 (YUV420p) color space to BGR. The function converts an input image from NV12 color space to BGR. The conventional ranges for Y, U, and V channel values are 0 to 255. More...
 
GMat NV12toGray (const GMat &src_y, const GMat &src_uv)
 Converts an image from NV12 (YUV420p) color space to gray-scaled. The function converts an input image from NV12 color space to gray-scaled. The conventional ranges for Y, U, and V channel values are 0 to 255. More...
 
GMat NV12toRGB (const GMat &src_y, const GMat &src_uv)
 Converts an image from NV12 (YUV420p) color space to RGB. The function converts an input image from NV12 color space to RGB. The conventional ranges for Y, U, and V channel values are 0 to 255. More...
 
GMatP NV12toRGBp (const GMat &src_y, const GMat &src_uv)
 Converts an image from NV12 (YUV420p) color space to RGB. The function converts an input image from NV12 color space to RGB. The conventional ranges for Y, U, and V channel values are 0 to 255. More...
 
bool operator!= (const GBackend &lhs, const GBackend &rhs)
 
std::tuple< GArray< Rect >, GArray< int > > parseSSD (const GMat &in, const GOpaque< Size > &inSz, const float confidenceThreshold=0.5f, const int filterLabel=-1)
 Parses output of SSD network. More...
 
GArray< RectparseSSD (const GMat &in, const GOpaque< Size > &inSz, const float confidenceThreshold=0.5f, const bool alignmentToSquare=false, const bool filterOutOfBounds=false)
 
std::tuple< GArray< Rect >, GArray< int > > parseYolo (const GMat &in, const GOpaque< Size > &inSz, const float confidenceThreshold=0.5f, const float nmsThreshold=0.5f, const std::vector< float > &anchors=nn::parsers::GParseYolo::defaultAnchors())
 Parses output of Yolo network. More...
 
GMat phase (const GMat &x, const GMat &y, bool angleInDegrees=false)
 Calculates the rotation angle of 2D vectors. More...
 
std::tuple< GMat, GMatpolarToCart (const GMat &magnitude, const GMat &angle, bool angleInDegrees=false)
 Calculates x and y coordinates of 2D vectors from their magnitude and angle. More...
 
GMat remap (const GMat &src, const Mat &map1, const Mat &map2, int interpolation, int borderMode=BORDER_CONSTANT, const Scalar &borderValue=Scalar())
 Applies a generic geometrical transformation to an image. More...
 
GMat resize (const GMat &src, const Size &dsize, double fx=0, double fy=0, int interpolation=INTER_LINEAR)
 Resizes an image. More...
 
GMatP resizeP (const GMatP &src, const Size &dsize, int interpolation=cv::INTER_LINEAR)
 Resizes a planar image. More...
 
GMat RGB2Gray (const GMat &src)
 Converts an image from RGB color space to gray-scaled. More...
 
GMat RGB2Gray (const GMat &src, float rY, float gY, float bY)
 
GMat RGB2HSV (const GMat &src)
 Converts an image from RGB color space to HSV. The function converts an input image from RGB color space to HSV. The conventional ranges for R, G, and B channel values are 0 to 255. More...
 
GMat RGB2I420 (const GMat &src)
 Converts an image from RGB color space to I420 color space. More...
 
GMat RGB2Lab (const GMat &src)
 Converts an image from RGB color space to Lab color space. More...
 
GMat RGB2YUV (const GMat &src)
 Converts an image from RGB color space to YUV color space. More...
 
GMat RGB2YUV422 (const GMat &src)
 Converts an image from RGB color space to YUV422. The function converts an input image from RGB color space to YUV422. The conventional ranges for R, G, and B channel values are 0 to 255. More...
 
GMat select (const GMat &src1, const GMat &src2, const GMat &mask)
 Select values from either first or second of input matrices by given mask. The function set to the output matrix either the value from the first input matrix if corresponding value of mask matrix is 255, or value from the second input matrix (if value of mask matrix set to 0). More...
 
GMat sepFilter (const GMat &src, int ddepth, const Mat &kernelX, const Mat &kernelY, const Point &anchor, const Scalar &delta, int borderType=BORDER_DEFAULT, const Scalar &borderValue=Scalar(0))
 Applies a separable linear filter to a matrix(image). More...
 
std::vector< char > serialize (const cv::GComputation &c)
 
std::vector< char > serialize (const cv::GCompileArgs &)
 
std::vector< char > serialize (const cv::GMetaArgs &)
 
std::vector< char > serialize (const cv::GRunArgs &)
 
std::vector< char > serialize (const std::vector< std::string > &)
 
GMat Sobel (const GMat &src, int ddepth, int dx, int dy, int ksize=3, double scale=1, double delta=0, int borderType=BORDER_DEFAULT, const Scalar &borderValue=Scalar(0))
 Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator. More...
 
std::tuple< GMat, GMatSobelXY (const GMat &src, int ddepth, int order, int ksize=3, double scale=1, double delta=0, int borderType=BORDER_DEFAULT, const Scalar &borderValue=Scalar(0))
 Calculates the first, second, third, or mixed image derivatives using an extended Sobel operator. More...
 
std::tuple< GMat, GMat, GMatsplit3 (const GMat &src)
 Divides a 3-channel matrix into 3 single-channel matrices. More...
 
std::tuple< GMat, GMat, GMat, GMatsplit4 (const GMat &src)
 Divides a 4-channel matrix into 4 single-channel matrices. More...
 
GMat sqrt (const GMat &src)
 Calculates a square root of array elements. More...
 
GMat stereo (const GMat &left, const GMat &right, const StereoOutputFormat of=StereoOutputFormat::DEPTH_FLOAT32)
 Extract disparity/depth information depending on passed StereoOutputFormat argument. The function extracts disparity/depth information depending on passed StereoOutputFormat argument from given stereo-pair. More...
 
GMat sub (const GMat &src1, const GMat &src2, int ddepth=-1)
 Calculates the per-element difference between two matrices. More...
 
GMat subC (const GMat &src, const GScalar &c, int ddepth=-1)
 Calculates the per-element difference between matrix and given scalar. More...
 
GMat subRC (const GScalar &c, const GMat &src, int ddepth=-1)
 Calculates the per-element difference between given scalar and the matrix. More...
 
GScalar sum (const GMat &src)
 Calculates sum of all matrix elements. More...
 
GMat threshold (const GMat &src, const GScalar &thresh, const GScalar &maxval, int type)
 Applies a fixed-level threshold to each matrix element. More...
 
std::tuple< GMat, GScalarthreshold (const GMat &src, const GScalar &maxval, int type)
 
GMat warpAffine (const GMat &src, const Mat &M, const Size &dsize, int flags=cv::INTER_LINEAR, int borderMode=cv::BORDER_CONSTANT, const Scalar &borderValue=Scalar())
 Applies an affine transformation to an image. More...
 
GMat warpPerspective (const GMat &src, const Mat &M, const Size &dsize, int flags=cv::INTER_LINEAR, int borderMode=cv::BORDER_CONSTANT, const Scalar &borderValue=Scalar())
 Applies a perspective transformation to an image. More...
 
GMat YUV2BGR (const GMat &src)
 Converts an image from YUV color space to BGR color space. More...
 
GMat YUV2RGB (const GMat &src)
 Converts an image from YUV color space to RGB. The function converts an input image from YUV color space to RGB. The conventional ranges for Y, U, and V channel values are 0 to 255. More...
 

Enumeration Type Documentation

◆ StereoOutputFormat

Enumerator
DEPTH_FLOAT16 
DEPTH_FLOAT32 
DISPARITY_FIXED16_11_5 
DISPARITY_FIXED16_12_4 

Function Documentation

◆ bind() [1/2]

cv::GRunArgsP cv::gapi::bind ( cv::GRunArgs results)

◆ bind() [2/2]

cv::GRunArg cv::gapi::bind ( cv::GRunArgP out)

◆ combine() [1/2]

GKernelPackage cv::gapi::combine ( const GKernelPackage lhs,
const GKernelPackage rhs 
)
Parameters
lhs"Left-hand-side" package in the process
rhs"Right-hand-side" package in the process
Returns
a new kernel package.

◆ combine() [2/2]

template<typename... Ps>
GKernelPackage cv::gapi::combine ( const GKernelPackage a,
const GKernelPackage b,
Ps &&...  rest 
)

Combines multiple G-API kernel packages into one.

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

This function successively combines the passed kernel packages using a right fold. Calling combine(a, b, c) is equal to combine(a, combine(b, c)).

Returns
The resulting kernel package

◆ deserialize() [1/7]

template<typename T >
static T cv::gapi::deserialize ( const std::vector< char > &  p)
inlinestatic

◆ deserialize() [2/7]

template<>
cv::GComputation cv::gapi::deserialize ( const std::vector< char > &  p)
inline

◆ deserialize() [3/7]

template<>
cv::GMetaArgs cv::gapi::deserialize ( const std::vector< char > &  p)
inline

◆ deserialize() [4/7]

template<>
cv::GRunArgs cv::gapi::deserialize ( const std::vector< char > &  p)
inline

◆ deserialize() [5/7]

template<>
std::vector<std::string> cv::gapi::deserialize ( const std::vector< char > &  p)
inline

◆ deserialize() [6/7]

template<typename T , typename... Types>
std::enable_if<std::is_same<T, GCompileArgs>::value, GCompileArgs>:: type cv::gapi::deserialize ( const std::vector< char > &  p)
inline

◆ deserialize() [7/7]

template<typename T , typename RMatAdapterType >
std::enable_if<std::is_same<T, GRunArgs>::value, GRunArgs>:: type cv::gapi::deserialize ( const std::vector< char > &  p)
inline

◆ equalizeHist()

GMat cv::gapi::equalizeHist ( const GMat src)

gapi_feature

The function equalizes the histogram of the input image using the following algorithm:

  • Calculate the histogram \(H\) for src .
  • Normalize the histogram so that the sum of histogram bins is 255.
  • Compute the integral of the histogram:

    \[H'_i = \sum _{0 \le j < i} H(j)\]

  • Transform the image using \(H'\) as a look-up table: \(\texttt{dst}(x,y) = H'(\texttt{src}(x,y))\)

The algorithm normalizes the brightness and increases the contrast of the image.

Note
  • The returned image is of the same size and type as input.
  • Function textual ID is "org.opencv.imgproc.equalizeHist"
Parameters
srcSource 8-bit single channel image.

◆ getCompileArg()

template<typename T >
cv::util::optional<T> cv::gapi::getCompileArg ( const cv::GCompileArgs args)
inline

Retrieves particular compilation argument by its type from cv::GCompileArgs.

◆ infer() [1/6]

template<typename Net , typename T >
Net::Result cv::gapi::infer ( cv::GOpaque< cv::Rect roi,
in 
)
Python:
retval=cv.gapi.infer(name, inputs)
retval=cv.gapi.infer(name, roi, inputs)
retval=cv.gapi.infer(name, rois, inputs)

Calculates response for the specified network (template parameter) for the specified region in the source image. Currently expects a single-input network only.

Template Parameters
Anetwork type defined with G_API_NET() macro.
Parameters
ininput image where to take ROI from.
roian object describing the region of interest in the source image. May be calculated in the same graph dynamically.
Returns
an object of return type as defined in G_API_NET(). If a network has multiple return values (defined with a tuple), a tuple of objects of appropriate type is returned.
See also
G_API_NET()

◆ infer() [2/6]

template<typename Net , typename... Args>
Net::ResultL cv::gapi::infer ( cv::GArray< cv::Rect roi,
Args &&...  args 
)
Python:
retval=cv.gapi.infer(name, inputs)
retval=cv.gapi.infer(name, roi, inputs)
retval=cv.gapi.infer(name, rois, inputs)

Calculates responses for the specified network (template parameter) for every region in the source image.

Template Parameters
Anetwork type defined with G_API_NET() macro.
Parameters
roia list of rectangles describing regions of interest in the source image. Usually an output of object detector or tracker.
argsnetwork's input parameters as specified in G_API_NET() macro. NOTE: verified to work reliably with 1-input topologies only.
Returns
a list of objects of return type as defined in G_API_NET(). If a network has multiple return values (defined with a tuple), a tuple of GArray<> objects is returned with the appropriate types inside.
See also
G_API_NET()

◆ infer() [3/6]

template<typename Net , typename... Args>
Net::Result cv::gapi::infer ( Args &&...  args)
Python:
retval=cv.gapi.infer(name, inputs)
retval=cv.gapi.infer(name, roi, inputs)
retval=cv.gapi.infer(name, rois, inputs)

Calculates response for the specified network (template parameter) given the input data.

Template Parameters
Anetwork type defined with G_API_NET() macro.
Parameters
argsnetwork's input parameters as specified in G_API_NET() macro.
Returns
an object of return type as defined in G_API_NET(). If a network has multiple return values (defined with a tuple), a tuple of objects of appropriate type is returned.
See also
G_API_NET()

◆ infer() [4/6]

template<typename T = Generic>
cv::GInferOutputs cv::gapi::infer ( const std::string &  tag,
const cv::GInferInputs inputs 
)
Python:
retval=cv.gapi.infer(name, inputs)
retval=cv.gapi.infer(name, roi, inputs)
retval=cv.gapi.infer(name, rois, inputs)

Calculates response for generic network.

Parameters
taga network tag
inputsnetworks's inputs
Returns
a GInferOutputs

◆ infer() [5/6]

template<typename T = Generic>
cv::GInferOutputs cv::gapi::infer ( const std::string &  tag,
const cv::GOpaque< cv::Rect > &  roi,
const cv::GInferInputs inputs 
)
Python:
retval=cv.gapi.infer(name, inputs)
retval=cv.gapi.infer(name, roi, inputs)
retval=cv.gapi.infer(name, rois, inputs)

Calculates response for the generic network for the specified region in the source image. Currently expects a single-input network only.

Parameters
taga network tag
roia an object describing the region of interest in the source image. May be calculated in the same graph dynamically.
inputsnetworks's inputs
Returns
a cv::GInferOutputs

◆ infer() [6/6]

template<typename T = Generic>
cv::GInferListOutputs cv::gapi::infer ( const std::string &  tag,
const cv::GArray< cv::Rect > &  rois,
const cv::GInferInputs inputs 
)
Python:
retval=cv.gapi.infer(name, inputs)
retval=cv.gapi.infer(name, roi, inputs)
retval=cv.gapi.infer(name, rois, inputs)

Calculates responses for the specified network for every region in the source image.

Parameters
taga network tag
roisa list of rectangles describing regions of interest in the source image. Usually an output of object detector or tracker.
inputsnetworks's inputs
Returns
a cv::GInferListOutputs

◆ infer2() [1/2]

template<typename Net , typename T , typename... Args>
Net::ResultL cv::gapi::infer2 ( image,
cv::GArray< Args >...  args 
)
Python:
retval=cv.gapi.infer2(name, in, inputs)

Calculates responses for the specified network (template parameter) for every region in the source image, extended version.

Template Parameters
Anetwork type defined with G_API_NET() macro.
Parameters
imageA source image containing regions of interest
argsGArray<> objects of cv::Rect or cv::GMat, one per every network input:
  • If a cv::GArray<cv::Rect> is passed, the appropriate regions are taken from image and preprocessed to this particular network input;
  • If a cv::GArray<cv::GMat> is passed, the underlying data traited as tensor (no automatic preprocessing happen).
Returns
a list of objects of return type as defined in G_API_NET(). If a network has multiple return values (defined with a tuple), a tuple of GArray<> objects is returned with the appropriate types inside.
See also
G_API_NET()

◆ infer2() [2/2]

template<typename T = Generic, typename Input >
std::enable_if<cv::detail::accepted_infer_types<Input>::value, cv::GInferListOutputs>::type cv::gapi::infer2 ( const std::string &  tag,
const Input &  in,
const cv::GInferListInputs inputs 
)
Python:
retval=cv.gapi.infer2(name, in, inputs)

Calculates responses for the specified network for every region in the source image, extended version.

Parameters
taga network tag
ina source image containing regions of interest.
inputsnetworks's inputs
Returns
a cv::GInferListOutputs

◆ island()

void cv::gapi::island ( const std::string &  name,
GProtoInputArgs &&  ins,
GProtoOutputArgs &&  outs 
)

Define an tagged island (subgraph) within a computation.

Declare an Island tagged with name and defined from ins to outs (exclusively, as ins/outs are data objects, and regioning is done on operations level). Throws if any operation between ins and outs are already assigned to another island.

Islands allow to partition graph into subgraphs, fine-tuning the way it is scheduled by the underlying executor.

Parameters
namename of the Island to create
insvector of input data objects where the subgraph begins
outsvector of output data objects where the subgraph ends.

The way how an island is defined is similar to how cv::GComputation is defined on input/output data objects. Same rules apply here as well – if there's no functional dependency between inputs and outputs or there's not enough input data objects were specified to properly calculate all outputs, an exception is thrown.

Use cv::GIn() / cv::GOut() to specify input/output vectors.

◆ kmeans() [1/4]

std::tuple<GOpaque<double>,GMat,GMat> cv::gapi::kmeans ( const GMat data,
const int  K,
const GMat bestLabels,
const TermCriteria criteria,
const int  attempts,
const KmeansFlags  flags 
)
Python:
retval=cv.gapi.kmeans(data, K, criteria, attempts, flags)
retval=cv.gapi.kmeans(data, K, bestLabels, criteria, attempts, flags)

Finds centers of clusters and groups input samples around the clusters.

The function kmeans implements a k-means algorithm that finds the centers of K clusters and groups the input samples around the clusters. As an output, \(\texttt{bestLabels}_i\) contains a 0-based cluster index for the \(i^{th}\) sample.

Note
  • Function textual ID is "org.opencv.core.kmeansND"
  • In case of an N-dimentional points' set given, input GMat can have the following traits: 2 dimensions, a single row or column if there are N channels, or N columns if there is a single channel. Mat should have CV_32F depth.
  • Although, if GMat with height != 1, width != 1, channels != 1 given as data, n-dimensional samples are considered given in amount of A, where A = height, n = width * channels.
  • In case of GMat given as data:
    • the output labels are returned as 1-channel GMat with sizes width = 1, height = A, where A is samples amount, or width = bestLabels.width, height = bestLabels.height if bestLabels given;
    • the cluster centers are returned as 1-channel GMat with sizes width = n, height = K, where n is samples' dimentionality and K is clusters' amount.
  • As one of possible usages, if you want to control the initial labels for each attempt by yourself, you can utilize just the core of the function. To do that, set the number of attempts to 1, initialize labels each time using a custom algorithm, pass them with the ( flags = KMEANS_USE_INITIAL_LABELS ) flag, and then choose the best (most-compact) clustering.
Parameters
dataData for clustering. An array of N-Dimensional points with float coordinates is needed. Function can take GArray<Point2f>, GArray<Point3f> for 2D and 3D cases or GMat for any dimentionality and channels.
KNumber of clusters to split the set by.
bestLabelsOptional input integer array that can store the supposed initial cluster indices for every sample. Used when ( flags = KMEANS_USE_INITIAL_LABELS ) flag is set.
criteriaThe algorithm termination criteria, that is, the maximum number of iterations and/or the desired accuracy. The accuracy is specified as criteria.epsilon. As soon as each of the cluster centers moves by less than criteria.epsilon on some iteration, the algorithm stops.
attemptsFlag to specify the number of times the algorithm is executed using different initial labellings. The algorithm returns the labels that yield the best compactness (see the first function return value).
flagsFlag that can take values of cv::KmeansFlags .
Returns
  • Compactness measure that is computed as

    \[\sum _i \| \texttt{samples} _i - \texttt{centers} _{ \texttt{labels} _i} \| ^2\]

    after every attempt. The best (minimum) value is chosen and the corresponding labels and the compactness value are returned by the function.
  • Integer array that stores the cluster indices for every sample.
  • Array of the cluster centers.

◆ kmeans() [2/4]

std::tuple<GOpaque<double>,GMat,GMat> cv::gapi::kmeans ( const GMat data,
const int  K,
const TermCriteria criteria,
const int  attempts,
const KmeansFlags  flags 
)
Python:
retval=cv.gapi.kmeans(data, K, criteria, attempts, flags)
retval=cv.gapi.kmeans(data, K, bestLabels, criteria, attempts, flags)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Note
  • Function textual ID is "org.opencv.core.kmeansNDNoInit"
  • KMEANS_USE_INITIAL_LABELS flag must not be set while using this overload.

◆ kmeans() [3/4]

std::tuple<GOpaque<double>,GArray<int>,GArray<Point2f> > cv::gapi::kmeans ( const GArray< Point2f > &  data,
const int  K,
const GArray< int > &  bestLabels,
const TermCriteria criteria,
const int  attempts,
const KmeansFlags  flags 
)
Python:
retval=cv.gapi.kmeans(data, K, criteria, attempts, flags)
retval=cv.gapi.kmeans(data, K, bestLabels, criteria, attempts, flags)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Note
Function textual ID is "org.opencv.core.kmeans2D"

◆ kmeans() [4/4]

std::tuple<GOpaque<double>,GArray<int>,GArray<Point3f> > cv::gapi::kmeans ( const GArray< Point3f > &  data,
const int  K,
const GArray< int > &  bestLabels,
const TermCriteria criteria,
const int  attempts,
const KmeansFlags  flags 
)
Python:
retval=cv.gapi.kmeans(data, K, criteria, attempts, flags)
retval=cv.gapi.kmeans(data, K, bestLabels, criteria, attempts, flags)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Note
Function textual ID is "org.opencv.core.kmeans3D"

◆ networks()

template<typename... Args>
cv::gapi::GNetPackage cv::gapi::networks ( Args &&...  args)
Python:
retval=cv.gapi.networks(params)

◆ operator!=()

bool cv::gapi::operator!= ( const GBackend lhs,
const GBackend rhs 
)
inline

◆ parseSSD() [1/2]

std::tuple<GArray<Rect>, GArray<int> > cv::gapi::parseSSD ( const GMat in,
const GOpaque< Size > &  inSz,
const float  confidenceThreshold = 0.5f,
const int  filterLabel = -1 
)
Python:
retval=cv.gapi.parseSSD(in, inSz[, confidenceThreshold[, alignmentToSquare[, filterOutOfBounds]]])

Parses output of SSD network.

Extracts detection information (box, confidence, label) from SSD output and filters it by given confidence and label.

Note
Function textual ID is "org.opencv.nn.parsers.parseSSD_BL"
Parameters
inInput CV_32F tensor with {1,1,N,7} dimensions.
inSzSize to project detected boxes to (size of the input image).
confidenceThresholdIf confidence of the detection is smaller than confidence threshold, detection is rejected.
filterLabelIf provided (!= -1), only detections with given label will get to the output.
Returns
a tuple with a vector of detected boxes and a vector of appropriate labels.

◆ parseSSD() [2/2]

GArray<Rect> cv::gapi::parseSSD ( const GMat in,
const GOpaque< Size > &  inSz,
const float  confidenceThreshold = 0.5f,
const bool  alignmentToSquare = false,
const bool  filterOutOfBounds = false 
)
Python:
retval=cv.gapi.parseSSD(in, inSz[, confidenceThreshold[, alignmentToSquare[, filterOutOfBounds]]])

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. Extracts detection information (box, confidence) from SSD output and filters it by given confidence and by going out of bounds.

Note
Function textual ID is "org.opencv.nn.parsers.parseSSD"
Parameters
inInput CV_32F tensor with {1,1,N,7} dimensions.
inSzSize to project detected boxes to (size of the input image).
confidenceThresholdIf confidence of the detection is smaller than confidence threshold, detection is rejected.
alignmentToSquareIf provided true, bounding boxes are extended to squares. The center of the rectangle remains unchanged, the side of the square is the larger side of the rectangle.
filterOutOfBoundsIf provided true, out-of-frame boxes are filtered.
Returns
a vector of detected bounding boxes.

◆ parseYolo()

std::tuple<GArray<Rect>, GArray<int> > cv::gapi::parseYolo ( const GMat in,
const GOpaque< Size > &  inSz,
const float  confidenceThreshold = 0.5f,
const float  nmsThreshold = 0.5f,
const std::vector< float > &  anchors = nn::parsers::GParseYolo::defaultAnchors() 
)

Parses output of Yolo network.

Extracts detection information (box, confidence, label) from Yolo output, filters it by given confidence and performs non-maximum supression for overlapping boxes.

Note
Function textual ID is "org.opencv.nn.parsers.parseYolo"
Parameters
inInput CV_32F tensor with {1,13,13,N} dimensions, N should satisfy:

\[\texttt{N} = (\texttt{num_classes} + \texttt{5}) * \texttt{5},\]

where num_classes - a number of classes Yolo network was trained with.
inSzSize to project detected boxes to (size of the input image).
confidenceThresholdIf confidence of the detection is smaller than confidence threshold, detection is rejected.
nmsThresholdNon-maximum supression threshold which controls minimum relative box intersection area required for rejecting the box with a smaller confidence. If 1.f, nms is not performed and no boxes are rejected.
anchorsAnchors Yolo network was trained with.
Note
The default anchor values are specified for YOLO v2 Tiny as described in Intel Open Model Zoo documentation.
Returns
a tuple with a vector of detected boxes and a vector of appropriate labels.

◆ serialize() [1/5]

std::vector<char> cv::gapi::serialize ( const cv::GComputation c)

◆ serialize() [2/5]

std::vector<char> cv::gapi::serialize ( const cv::GCompileArgs )

◆ serialize() [3/5]

std::vector<char> cv::gapi::serialize ( const cv::GMetaArgs )

◆ serialize() [4/5]

std::vector<char> cv::gapi::serialize ( const cv::GRunArgs )

◆ serialize() [5/5]

std::vector<char> cv::gapi::serialize ( const std::vector< std::string > &  )

◆ stereo()

GMat cv::gapi::stereo ( const GMat left,
const GMat right,
const StereoOutputFormat  of = StereoOutputFormat::DEPTH_FLOAT32 
)

Extract disparity/depth information depending on passed StereoOutputFormat argument. The function extracts disparity/depth information depending on passed StereoOutputFormat argument from given stereo-pair.

Parameters
leftleft 8-bit unsigned 1-channel image of CV_8UC1 type
rightright 8-bit unsigned 1-channel image of CV_8UC1 type
ofenum to specify output kind: depth or disparity and corresponding type