cv::gapi::streaming Namespace Reference

This namespace contains G-API functions, structures, and symbols related to the Streaming execution mode. More...

Namespaces
namespace	detail
namespace	meta_tag

Classes
struct	queue_capacity
	Specify queue capacity for streaming execution. More...

Enumerations
enum class	sync_policy {   dont_sync ,   drop }

Functions
cv::GMat	BGR (const cv::GFrame &in)
	Gets bgr plane from input frame.
GFrame	desync (const GFrame &f)
GMat	desync (const GMat &g)
	Starts a desynchronized branch in the graph.
	G_API_OP (GUV,< GMat(GFrame)>, "org.opencv.streaming.UV")
	G_API_OP (GY,< GMat(GFrame)>, "org.opencv.streaming.Y")
	G_TYPED_KERNEL (GSize,< GOpaque< Size >(GMat)>, "org.opencv.streaming.size")
	G_TYPED_KERNEL (GSizeMF,< GOpaque< Size >(GFrame)>, "org.opencv.streaming.sizeMF")
	G_TYPED_KERNEL (GSizeR,< GOpaque< Size >(GOpaque< Rect >)>, "org.opencv.streaming.sizeR")
cv::GKernelPackage	kernels ()
template<typename T, typename G>
cv::GOpaque< T >	meta (G g, const std::string &tag)
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.
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.
template<typename G>
cv::GOpaque< int64_t >	seq_id (G g)
template<typename G>
cv::GOpaque< int64_t >	seqNo (G g)
GOpaque< Size >	size (const GFrame &src)
	Gets dimensions from MediaFrame.
GOpaque< Size >	size (const GMat &src)
	Gets dimensions from Mat.
GOpaque< Size >	size (const GOpaque< Rect > &r)
template<typename G>
cv::GOpaque< int64_t >	timestamp (G g)
GMat	UV (const cv::GFrame &frame)
	Extracts UV plane from media frame.
GMat	Y (const cv::GFrame &frame)
	Extracts Y plane from media frame.

Detailed Description

This namespace contains G-API functions, structures, and symbols related to the Streaming execution mode.

Some of the operations defined in this namespace (e.g. size(), BGR(), etc.) can be used in the traditional execution mode too.

Enumeration Type Documentation

sync_policy

enum class cv::gapi::streaming::sync_policy

strong

Enumerator
dont_sync
drop

Function Documentation

BGR()

cv::GMat cv::gapi::streaming::BGR

(

const cv::GFrame &

in

)

Gets bgr plane from input frame.

Note

Function textual ID is "org.opencv.streaming.BGR"

Parameters

in	Input frame

Returns

Image in BGR format

desync() [1/2]

GFrame cv::gapi::streaming::desync

(

const GFrame &

f

)

Python:
	cv.gapi.streaming.desync(	g	) ->	retval

desync() [2/2]

GMat cv::gapi::streaming::desync

(

const GMat &

g

)

Python:
	cv.gapi.streaming.desync(	g	) ->	retval

Starts a desynchronized branch in the graph.

This operation takes a single G-API data object and returns a graph-level "duplicate" of this object.

Operations which use this data object can be desynchronized from the rest of the graph.

This operation has no effect when a GComputation is compiled with regular cv::GComputation::compile(), since cv::GCompiled objects always produce their full output vectors.

This operation only makes sense when a GComputation is compiled in streaming mode with cv::GComputation::compileStreaming(). If this operation is used and there are desynchronized outputs, the user should use a special version of cv::GStreamingCompiled::pull() which produces an array of cv::util::optional<> objects.

Note

This feature is highly experimental now and is currently limited to a single GMat/GFrame argument only.

G_API_OP() [1/2]

cv::gapi::streaming::G_API_OP	(	GUV	,
		< GMat(GFrame)>	,
		"org.opencv.streaming.UV"	)

G_API_OP() [2/2]

cv::gapi::streaming::G_API_OP	(	GY	,
		< GMat(GFrame)>	,
		"org.opencv.streaming.Y"	)

G_TYPED_KERNEL() [1/3]

cv::gapi::streaming::G_TYPED_KERNEL	(	GSize	,
		< GOpaque< Size >(GMat)>	,
		"org.opencv.streaming.size"	)

Here is the call graph for this function:

G_TYPED_KERNEL() [2/3]

cv::gapi::streaming::G_TYPED_KERNEL	(	GSizeMF	,
		< GOpaque< Size >(GFrame)>	,
		"org.opencv.streaming.sizeMF"	)

Here is the call graph for this function:

G_TYPED_KERNEL() [3/3]

cv::gapi::streaming::G_TYPED_KERNEL	(	GSizeR	,
		< GOpaque< Size >(GOpaque< Rect >)>	,
		"org.opencv.streaming.sizeR"	)

Here is the call graph for this function:

kernels()

cv::GKernelPackage cv::gapi::streaming::kernels

(

)

meta()

template<typename T, typename G>

cv::GOpaque< T > cv::gapi::streaming::meta	(	G	g,
		const std::string &	tag )

Here is the call graph for this function:

parseSSD()

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 )

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

in	Input CV_32F tensor with {1,1,N,7} dimensions.
inSz	Size to project detected boxes to (size of the input image).
confidenceThreshold	If confidence of the detection is smaller than confidence threshold, detection is rejected.
filterLabel	If 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.

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 suppression for overlapping boxes.

Note

Function textual ID is "org.opencv.nn.parsers.parseYolo"

Parameters

in	Input 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.
inSz	Size to project detected boxes to (size of the input image).
confidenceThreshold	If confidence of the detection is smaller than confidence threshold, detection is rejected.
nmsThreshold	Non-maximum suppression 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.
anchors	Anchors 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.

seq_id()

template<typename G>

cv::GOpaque< int64_t > cv::gapi::streaming::seq_id

(

G

g

)

Python:
	cv.gapi.streaming.seq_id(	arg1	) ->	retval

Here is the call graph for this function:

seqNo()

template<typename G>

cv::GOpaque< int64_t > cv::gapi::streaming::seqNo

(

G

g

)

Python:
	cv.gapi.streaming.seqNo(	arg1	) ->	retval

Here is the call graph for this function:

size() [1/3]

GOpaque< Size > cv::gapi::streaming::size

(

const GFrame &

src

)

Python:
	cv.gapi.streaming.size(	src	) ->	retval
	cv.gapi.streaming.size(	r	) ->	retval

Gets dimensions from MediaFrame.

Note

Function textual ID is "org.opencv.streaming.sizeMF"

Parameters

src	Input frame

Returns

Size (frame dimensions).

size() [2/3]

GOpaque< Size > cv::gapi::streaming::size

(

const GMat &

src

)

Python:
	cv.gapi.streaming.size(	src	) ->	retval
	cv.gapi.streaming.size(	r	) ->	retval

Gets dimensions from Mat.

Note

Function textual ID is "org.opencv.streaming.size"

Parameters

src	Input tensor

Returns

Size (tensor dimensions).

size() [3/3]

GOpaque< Size > cv::gapi::streaming::size

(

const GOpaque< Rect > &

r

)

Python:
	cv.gapi.streaming.size(	src	) ->	retval
	cv.gapi.streaming.size(	r	) ->	retval

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

Note

Function textual ID is "org.opencv.streaming.sizeR"

Parameters

r	Input rectangle.

Returns

Size (rectangle dimensions).

timestamp()

template<typename G>

cv::GOpaque< int64_t > cv::gapi::streaming::timestamp

(

G

g

)

Python:
	cv.gapi.streaming.timestamp(	arg1	) ->	retval

Here is the call graph for this function:

UV()

GMat cv::gapi::streaming::UV

(

const cv::GFrame &

frame

)

Extracts UV plane from media frame.

Output image is 8-bit 2-channel image of CV_8UC2.

Note

Function textual ID is "org.opencv.streaming.UV"

Parameters

frame

input media frame.

Y()

GMat cv::gapi::streaming::Y

(

const cv::GFrame &

frame

)

Extracts Y plane from media frame.

Output image is 8-bit 1-channel image of CV_8UC1.

Note

Function textual ID is "org.opencv.streaming.Y"

Parameters

frame

input media frame.