Pose estimation DNN. More...

Classes
class	poseNet
	Pose estimation models with TensorRT support. More...

Macros
#define	POSENET_DEFAULT_INPUT "input"
	Name of default input blob for pose estimation ONNX model. More...

#define	POSENET_DEFAULT_CMAP "cmap"
	Name of default output blob of the confidence map for pose estimation ONNX model. More...

#define	POSENET_DEFAULT_PAF "paf"
	Name of default output blob of the Part Affinity Field (PAF) for pose estimation ONNX model. More...

#define	POSENET_DEFAULT_THRESHOLD 0.15f
	Default value of the minimum confidence threshold. More...

#define	POSENET_DEFAULT_KEYPOINT_SCALE 0.0052f
	Default scale used for drawing keypoint circles. More...

#define	POSENET_DEFAULT_LINK_SCALE 0.0013f
	Default scale used for drawing link lines. More...

#define	POSENET_MODEL_TYPE "pose"
	The model type for poseNet in data/networks/models.json. More...

Detailed Description

Pose estimation DNN.

Class Documentation

◆ poseNet

class poseNet

Pose estimation models with TensorRT support.

Inheritance diagram for poseNet:

Public Types
enum	OverlayFlags { OVERLAY_NONE = 0, OVERLAY_BOX = (1 << 0), OVERLAY_LINKS = (1 << 1), OVERLAY_KEYPOINTS = (1 << 2), OVERLAY_DEFAULT = OVERLAY_LINKS\|OVERLAY_KEYPOINTS }
	Overlay flags (can be OR'd together). More...

Public Member Functions
virtual	~poseNet ()
	Destory. More...

template<typename T >
bool	Process (T *image, uint32_t width, uint32_t height, std::vector< ObjectPose > &poses, uint32_t overlay=OVERLAY_DEFAULT)
	Perform pose estimation on the given image, returning object poses, and overlay the results. More...

bool	Process (void *image, uint32_t width, uint32_t height, imageFormat format, std::vector< ObjectPose > &poses, uint32_t overlay=OVERLAY_DEFAULT)
	Perform pose estimation on the given image, and overlay the results. More...

template<typename T >
bool	Process (T *image, uint32_t width, uint32_t height, uint32_t overlay=OVERLAY_DEFAULT)
	Perform pose estimation on the given image, and overlay the results. More...

bool	Process (void *image, uint32_t width, uint32_t height, imageFormat format, uint32_t overlay=OVERLAY_DEFAULT)
	Perform pose estimation on the given image, and overlay the results. More...

template<typename T >
bool	Overlay (T input, T output, uint32_t width, uint32_t height, const std::vector< ObjectPose > &poses, uint32_t overlay=OVERLAY_DEFAULT)
	Overlay the results on the image. More...

bool	Overlay (void input, void output, uint32_t width, uint32_t height, imageFormat format, const std::vector< ObjectPose > &poses, uint32_t overlay=OVERLAY_DEFAULT)
	Overlay the results on the image. More...

float	GetThreshold () const
	Retrieve the minimum confidence threshold. More...

void	SetThreshold (float threshold)
	Set the minimum confidence threshold. More...

const char *	GetCategory () const
	Get the category of objects that are detected (e.g. More...

uint32_t	GetNumKeypoints () const
	Get the number of keypoints in the topology. More...

const char *	GetKeypointName (uint32_t index) const
	Get the name of a keypoint in the topology by it's ID. More...

int	FindKeypointID (const char *name) const
	Find the ID of a keypoint by name, or return -1 if not found. More...

float4	GetKeypointColor (uint32_t index) const
	Get the overlay color of a keypoint. More...

void	SetKeypointColor (uint32_t index, const float4 &color)
	Set the overlay color for a keypoint. More...

void	SetKeypointAlpha (uint32_t index, float alpha)
	Set the alpha channel for a keypoint color (between 0-255). More...

void	SetKeypointAlpha (float alpha)
	Set the alpha channel for all keypoints colors used during overlay. More...

float	GetKeypointScale () const
	Get the scale used to calculate the radius of keypoints relative to input image dimensions. More...

void	SetKeypointScale (float scale)
	Set the scale used to calculate the radius of keypoint circles. More...

float	GetLinkScale () const
	Get the scale used to calculate the width of link lines relative to input image dimensions. More...

void	SetLinkScale (float scale)
	Set the scale used to calculate the width of link lines. More...

Public Member Functions inherited from tensorNet
virtual	~tensorNet ()
	Destory. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean=NULL, const char input_blob="data", const char output_blob="prob", uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const char input_blob, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance with multiple output layers. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance with multiple input layers. More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const char input_blob, const Dims3 &input_dims, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator *calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance (this variant is used for UFF models) More...

bool	LoadNetwork (const char prototxt, const char model, const char mean, const std::vector< std::string > &input_blobs, const std::vector< Dims3 > &input_dims, const std::vector< std::string > &output_blobs, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true, nvinfer1::IInt8Calibrator calibrator=NULL, cudaStream_t stream=NULL)
	Load a new network instance with multiple input layers (used for UFF models) More...

bool	LoadEngine (const char engine_filename, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, nvinfer1::IPluginFactory pluginFactory=NULL, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL)
	Load a network instance from a serialized engine plan file. More...

bool	LoadEngine (char engine_stream, size_t engine_size, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, nvinfer1::IPluginFactory pluginFactory=NULL, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL)
	Load a network instance from a serialized engine plan file. More...

bool	LoadEngine (nvinfer1::ICudaEngine *engine, const std::vector< std::string > &input_blobs, const std::vector< std::string > &output_blobs, deviceType device=DEVICE_GPU, cudaStream_t stream=NULL)
	Load network resources from an existing TensorRT engine instance. More...

bool	LoadEngine (const char filename, char stream, size_t size)
	Load a serialized engine plan file into memory. More...

void	EnableLayerProfiler ()
	Manually enable layer profiling times. More...

void	EnableDebug ()
	Manually enable debug messages and synchronization. More...

bool	AllowGPUFallback () const
	Return true if GPU fallback is enabled. More...

deviceType	GetDevice () const
	Retrieve the device being used for execution. More...

precisionType	GetPrecision () const
	Retrieve the type of precision being used. More...

bool	IsPrecision (precisionType type) const
	Check if a particular precision is being used. More...

cudaStream_t	GetStream () const
	Retrieve the stream that the device is operating on. More...

cudaStream_t	CreateStream (bool nonBlocking=true)
	Create and use a new stream for execution. More...

void	SetStream (cudaStream_t stream)
	Set the stream that the device is operating on. More...

const char *	GetPrototxtPath () const
	Retrieve the path to the network prototxt file. More...

const char *	GetModelPath () const
	Retrieve the full path to model file, including the filename. More...

const char *	GetModelFilename () const
	Retrieve the filename of the file, excluding the directory. More...

modelType	GetModelType () const
	Retrieve the format of the network model. More...

bool	IsModelType (modelType type) const
	Return true if the model is of the specified format. More...

uint32_t	GetInputLayers () const
	Retrieve the number of input layers to the network. More...

uint32_t	GetOutputLayers () const
	Retrieve the number of output layers to the network. More...

Dims3	GetInputDims (uint32_t layer=0) const
	Retrieve the dimensions of network input layer. More...

uint32_t	GetInputWidth (uint32_t layer=0) const
	Retrieve the width of network input layer. More...

uint32_t	GetInputHeight (uint32_t layer=0) const
	Retrieve the height of network input layer. More...

uint32_t	GetInputSize (uint32_t layer=0) const
	Retrieve the size (in bytes) of network input layer. More...

float *	GetInputPtr (uint32_t layer=0) const
	Get the CUDA pointer to the input layer's memory. More...

Dims3	GetOutputDims (uint32_t layer=0) const
	Retrieve the dimensions of network output layer. More...

uint32_t	GetOutputWidth (uint32_t layer=0) const
	Retrieve the width of network output layer. More...

uint32_t	GetOutputHeight (uint32_t layer=0) const
	Retrieve the height of network output layer. More...

uint32_t	GetOutputSize (uint32_t layer=0) const
	Retrieve the size (in bytes) of network output layer. More...

float *	GetOutputPtr (uint32_t layer=0) const
	Get the CUDA pointer to the output memory. More...

float	GetNetworkFPS ()
	Retrieve the network frames per second (FPS). More...

float	GetNetworkTime ()
	Retrieve the network runtime (in milliseconds). More...

const char *	GetNetworkName () const
	Retrieve the network name (it's filename). More...

float2	GetProfilerTime (profilerQuery query)
	Retrieve the profiler runtime (in milliseconds). More...

float	GetProfilerTime (profilerQuery query, profilerDevice device)
	Retrieve the profiler runtime (in milliseconds). More...

void	PrintProfilerTimes ()
	Print the profiler times (in millseconds). More...

Static Public Member Functions
static uint32_t	OverlayFlagsFromStr (const char *flags)
	Parse a string sequence into OverlayFlags enum. More...

static poseNet *	Create (const char *network="resnet18-body", float threshold=POSENET_DEFAULT_THRESHOLD, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true)
	Load a pre-trained model. More...

static poseNet *	Create (const char model_path, const char topology, const char colors, float threshold=POSENET_DEFAULT_THRESHOLD, const char input=POSENET_DEFAULT_INPUT, const char cmap=POSENET_DEFAULT_CMAP, const char paf=POSENET_DEFAULT_PAF, uint32_t maxBatchSize=DEFAULT_MAX_BATCH_SIZE, precisionType precision=TYPE_FASTEST, deviceType device=DEVICE_GPU, bool allowGPUFallback=true)
	Load a custom network instance. More...

static poseNet *	Create (int argc, char **argv)
	Load a new network instance by parsing the command line. More...

static poseNet *	Create (const commandLine &cmdLine)
	Load a new network instance by parsing the command line. More...

static const char *	Usage ()
	Usage string for command line arguments to Create() More...

Static Public Member Functions inherited from tensorNet
static bool	LoadClassLabels (const char *filename, std::vector< std::string > &descriptions, int expectedClasses=-1)
	Load class descriptions from a label file. More...

static bool	LoadClassLabels (const char *filename, std::vector< std::string > &descriptions, std::vector< std::string > &synsets, int expectedClasses=-1)
	Load class descriptions and synset strings from a label file. More...

static bool	LoadClassColors (const char filename, float4 colors, int expectedClasses, float defaultAlpha=255.0f)
	Load class colors from a text file. More...

static bool	LoadClassColors (const char filename, float4 *colors, int expectedClasses, float defaultAlpha=255.0f)
	Load class colors from a text file. More...

static float4	GenerateColor (uint32_t classID, float alpha=255.0f)
	Procedurally generate a color for a given class index with the specified alpha value. More...

static precisionType	SelectPrecision (precisionType precision, deviceType device=DEVICE_GPU, bool allowInt8=true)
	Resolve a desired precision to a specific one that's available. More...

static precisionType	FindFastestPrecision (deviceType device=DEVICE_GPU, bool allowInt8=true)
	Determine the fastest native precision on a device. More...

static std::vector< precisionType >	DetectNativePrecisions (deviceType device=DEVICE_GPU)
	Detect the precisions supported natively on a device. More...

static bool	DetectNativePrecision (const std::vector< precisionType > &nativeTypes, precisionType type)
	Detect if a particular precision is supported natively. More...

static bool	DetectNativePrecision (precisionType precision, deviceType device=DEVICE_GPU)
	Detect if a particular precision is supported natively. More...

Protected Member Functions
	poseNet ()

bool	init (const char model_path, const char topology, const char colors, float threshold, const char input, const char cmap, const char paf, uint32_t maxBatchSize, precisionType precision, deviceType device, bool allowGPUFallback)

bool	postProcess (std::vector< ObjectPose > &poses, uint32_t width, uint32_t height)

bool	loadTopology (const char json_path, Topology topology)

bool	loadKeypointColors (const char *filename)

Protected Member Functions inherited from tensorNet
	tensorNet ()
	Constructor. More...

bool	ProcessNetwork (bool sync=true)
	Execute processing of the network. More...

bool	ProfileModel (const std::string &deployFile, const std::string &modelFile, const std::vector< std::string > &inputs, const std::vector< Dims3 > &inputDims, const std::vector< std::string > &outputs, uint32_t maxBatchSize, precisionType precision, deviceType device, bool allowGPUFallback, nvinfer1::IInt8Calibrator calibrator, char engineStream, size_t engineSize)
	Create and output an optimized network model. More...

bool	ConfigureBuilder (nvinfer1::IBuilder builder, uint32_t maxBatchSize, uint32_t workspaceSize, precisionType precision, deviceType device, bool allowGPUFallback, nvinfer1::IInt8Calibrator calibrator)
	Configure builder options. More...

bool	ValidateEngine (const char model_path, const char cache_path, const char *checksum_path)
	Validate that the model already has a built TensorRT engine that exists and doesn't need updating. More...

void	PROFILER_BEGIN (profilerQuery query)
	Begin a profiling query, before network is run. More...

void	PROFILER_END (profilerQuery query)
	End a profiling query, after the network is run. More...

bool	PROFILER_QUERY (profilerQuery query)
	Query the CUDA part of a profiler query. More...

Protected Attributes
Topology	mTopology

float	mThreshold

float	mLinkScale

float	mKeypointScale

float4 *	mKeypointColors

int *	mPeaks

int *	mPeakCounts

int *	mConnections

int *	mObjects

int	mNumObjects

float *	mRefinedPeaks

float *	mScoreGraph

void *	mAssignmentWorkspace

void *	mConnectionWorkspace

Protected Attributes inherited from tensorNet
tensorNet::Logger	gLogger

tensorNet::Profiler	gProfiler

std::string	mPrototxtPath

std::string	mModelPath

std::string	mModelFile

std::string	mMeanPath

std::string	mCacheEnginePath

std::string	mCacheCalibrationPath

std::string	mChecksumPath

deviceType	mDevice

precisionType	mPrecision

modelType	mModelType

cudaStream_t	mStream

cudaEvent_t	mEventsGPU [PROFILER_TOTAL *2]

timespec	mEventsCPU [PROFILER_TOTAL *2]

nvinfer1::IRuntime *	mInfer

nvinfer1::ICudaEngine *	mEngine

nvinfer1::IExecutionContext *	mContext

float2	mProfilerTimes [PROFILER_TOTAL+1]

uint32_t	mProfilerQueriesUsed

uint32_t	mProfilerQueriesDone

uint32_t	mWorkspaceSize

uint32_t	mMaxBatchSize

bool	mEnableProfiler

bool	mEnableDebug

bool	mAllowGPUFallback

void **	mBindings

std::vector< layerInfo >	mInputs

std::vector< layerInfo >	mOutputs

Static Protected Attributes
static const int	CMAP_WINDOW_SIZE =5

static const int	PAF_INTEGRAL_SAMPLES =7

static const int	MAX_LINKS =100

static const int	MAX_OBJECTS =100

Member Enumeration Documentation

◆ OverlayFlags

enum poseNet::OverlayFlags

Overlay flags (can be OR'd together).

Enumerator
OVERLAY_NONE	No overlay.
OVERLAY_BOX	Overlay object bounding boxes.
OVERLAY_LINKS	Overlay the skeleton links (bones) as lines
OVERLAY_KEYPOINTS	Overlay the keypoints (joints) as circles.
OVERLAY_DEFAULT

Constructor & Destructor Documentation

◆ ~poseNet()

virtual poseNet::~poseNet ( )

virtual

Destory.

◆ poseNet()

poseNet::poseNet ( )

protected

Member Function Documentation

◆ Create() [1/4]

static poseNet* poseNet::Create	(	const char *	model_path,
		const char *	topology,
		const char *	colors,
		float	threshold = `POSENET_DEFAULT_THRESHOLD`,
		const char *	input = `POSENET_DEFAULT_INPUT`,
		const char *	cmap = `POSENET_DEFAULT_CMAP`,
		const char *	paf = `POSENET_DEFAULT_PAF`,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`
	)

static

Load a custom network instance.

Parameters

model_path	File path to the ONNX model
topology	File path to the topology JSON
colors	File path to the keypoint colors text file
threshold	default minimum confidence thrshold
input	Name of the input layer blob.
cmap	Name of the output confidence map layer.
paf	Name of the output Part Affinity Field (PAF) layer.
maxBatchSize	The maximum batch size that the network will support and be optimized for.

◆ Create() [2/4]

static poseNet* poseNet::Create	(	const char *	network = `"resnet18-body"`,
		float	threshold = `POSENET_DEFAULT_THRESHOLD`,
		uint32_t	maxBatchSize = `DEFAULT_MAX_BATCH_SIZE`,
		precisionType	precision = `TYPE_FASTEST`,
		deviceType	device = `DEVICE_GPU`,
		bool	allowGPUFallback = `true`
	)

static

Load a pre-trained model.

Parameters

network type of pre-supported network to load (

See also: POSENET_USAGE_STRING for models)

Parameters

threshold	default minimum threshold for detection
maxBatchSize	The maximum batch size that the network will support and be optimized for.

◆ Create() [3/4]

static poseNet* poseNet::Create ( const commandLine & cmdLine )

static

Load a new network instance by parsing the command line.

◆ Create() [4/4]

static poseNet* poseNet::Create	(	int	argc,
		char **	argv
	)

static

Load a new network instance by parsing the command line.

◆ FindKeypointID()

int poseNet::FindKeypointID ( const char * name ) const

inline

Find the ID of a keypoint by name, or return -1 if not found.

◆ GetCategory()

const char* poseNet::GetCategory ( ) const

inline

Get the category of objects that are detected (e.g.

'person', 'hand')

◆ GetKeypointColor()

float4 poseNet::GetKeypointColor ( uint32_t index ) const

inline

Get the overlay color of a keypoint.

◆ GetKeypointName()

const char* poseNet::GetKeypointName ( uint32_t index ) const

inline

Get the name of a keypoint in the topology by it's ID.

◆ GetKeypointScale()

float poseNet::GetKeypointScale ( ) const

inline

Get the scale used to calculate the radius of keypoints relative to input image dimensions.

◆ GetLinkScale()

float poseNet::GetLinkScale ( ) const

inline

Get the scale used to calculate the width of link lines relative to input image dimensions.

◆ GetNumKeypoints()

uint32_t poseNet::GetNumKeypoints ( ) const

inline

Get the number of keypoints in the topology.

◆ GetThreshold()

float poseNet::GetThreshold ( ) const

inline

Retrieve the minimum confidence threshold.

◆ init()

bool poseNet::init	(	const char *	model_path,
		const char *	topology,
		const char *	colors,
		float	threshold,
		const char *	input,
		const char *	cmap,
		const char *	paf,
		uint32_t	maxBatchSize,
		precisionType	precision,
		deviceType	device,
		bool	allowGPUFallback
	)

protected

◆ loadKeypointColors()

bool poseNet::loadKeypointColors ( const char * filename )

protected

◆ loadTopology()

bool poseNet::loadTopology	(	const char *	json_path,
		Topology *	topology
	)

protected

◆ Overlay() [1/2]

template<typename T >

bool poseNet::Overlay	(	T *	input,
		T *	output,
		uint32_t	width,
		uint32_t	height,
		const std::vector< ObjectPose > &	poses,
		uint32_t	overlay = `OVERLAY_DEFAULT`
	)

inline

Overlay the results on the image.

◆ Overlay() [2/2]

bool poseNet::Overlay	(	void *	input,
		void *	output,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		const std::vector< ObjectPose > &	poses,
		uint32_t	overlay = `OVERLAY_DEFAULT`
	)

Overlay the results on the image.

◆ OverlayFlagsFromStr()

static uint32_t poseNet::OverlayFlagsFromStr ( const char * flags )

static

Parse a string sequence into OverlayFlags enum.

Valid flags are "none", "box", "label", and "conf" and it is possible to combine flags (bitwise OR) together with commas or pipe (|) symbol. For example, the string sequence "box,label,conf" would return the flags OVERLAY_BOX|OVERLAY_LABEL|OVERLAY_CONFIDENCE.

◆ postProcess()

bool poseNet::postProcess	(	std::vector< ObjectPose > &	poses,
		uint32_t	width,
		uint32_t	height
	)

protected

◆ Process() [1/4]

template<typename T >

bool poseNet::Process	(	T *	image,
		uint32_t	width,
		uint32_t	height,
		std::vector< ObjectPose > &	poses,
		uint32_t	overlay = `OVERLAY_DEFAULT`
	)

inline

Perform pose estimation on the given image, returning object poses, and overlay the results.

Parameters

[in]	image	input image in CUDA device memory (uchar3/uchar4/float3/float4)
[in]	width	width of the input image in pixels.
[in]	height	height of the input image in pixels.
[out]	poses	array of ObjectPose structs that will be filled for each detected object.
[in]	overlay	bitwise OR combination of overlay flags (

See also: OverlayFlags and; Overlay()), or OVERLAY_NONE.

Returns: True on success, or false if an error occurred.

◆ Process() [2/4]

template<typename T >

bool poseNet::Process	(	T *	image,
		uint32_t	width,
		uint32_t	height,
		uint32_t	overlay = `OVERLAY_DEFAULT`
	)

inline

Perform pose estimation on the given image, and overlay the results.

Parameters

[in]	image	input image in CUDA device memory (uchar3/uchar4/float3/float4)
[in]	width	width of the input image in pixels.
[in]	height	height of the input image in pixels.
[in]	overlay	bitwise OR combination of overlay flags (

See also: OverlayFlags and; Overlay()), or OVERLAY_NONE.

Returns: True on success, or false if an error occurred.

◆ Process() [3/4]

bool poseNet::Process	(	void *	image,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		std::vector< ObjectPose > &	poses,
		uint32_t	overlay = `OVERLAY_DEFAULT`
	)

Perform pose estimation on the given image, and overlay the results.

Parameters

[in]	image	input image in CUDA device memory (uchar3/uchar4/float3/float4)
[in]	width	width of the input image in pixels.
[in]	height	height of the input image in pixels.
[out]	poses	array of ObjectPose structs that will be filled for each detected object.
[in]	overlay	bitwise OR combination of overlay flags (

See also: OverlayFlags and; Overlay()), or OVERLAY_NONE.

Returns: True on success, or false if an error occurred.

◆ Process() [4/4]

bool poseNet::Process	(	void *	image,
		uint32_t	width,
		uint32_t	height,
		imageFormat	format,
		uint32_t	overlay = `OVERLAY_DEFAULT`
	)

Perform pose estimation on the given image, and overlay the results.

Parameters

[in]	image	input image in CUDA device memory (uchar3/uchar4/float3/float4)
[in]	width	width of the input image in pixels.
[in]	height	height of the input image in pixels.
[in]	overlay	bitwise OR combination of overlay flags (

See also: OverlayFlags and; Overlay()), or OVERLAY_NONE.

Returns: True on success, or false if an error occurred.

◆ SetKeypointAlpha() [1/2]

void poseNet::SetKeypointAlpha ( float alpha )

inline

Set the alpha channel for all keypoints colors used during overlay.

◆ SetKeypointAlpha() [2/2]

void poseNet::SetKeypointAlpha	(	uint32_t	index,
		float	alpha
	)

inline

Set the alpha channel for a keypoint color (between 0-255).

◆ SetKeypointColor()

void poseNet::SetKeypointColor	(	uint32_t	index,
		const float4 &	color
	)

inline

Set the overlay color for a keypoint.

◆ SetKeypointScale()

void poseNet::SetKeypointScale ( float scale )

inline

Set the scale used to calculate the radius of keypoint circles.

This scale will be multiplied by the largest image dimension.

◆ SetLinkScale()

void poseNet::SetLinkScale ( float scale )

inline

Set the scale used to calculate the width of link lines.

This scale will be multiplied by the largest image dimension.

◆ SetThreshold()

void poseNet::SetThreshold ( float threshold )

inline

Set the minimum confidence threshold.

◆ Usage()

static const char* poseNet::Usage ( )

inlinestatic

Usage string for command line arguments to Create()

Member Data Documentation

◆ CMAP_WINDOW_SIZE

const int poseNet::CMAP_WINDOW_SIZE =5

staticprotected

◆ mAssignmentWorkspace

void* poseNet::mAssignmentWorkspace

protected

◆ MAX_LINKS

const int poseNet::MAX_LINKS =100

staticprotected

◆ MAX_OBJECTS

const int poseNet::MAX_OBJECTS =100

staticprotected

◆ mConnections

int* poseNet::mConnections

protected

◆ mConnectionWorkspace

void* poseNet::mConnectionWorkspace

protected

◆ mKeypointColors

float4* poseNet::mKeypointColors

protected

◆ mKeypointScale

float poseNet::mKeypointScale

protected

◆ mLinkScale

float poseNet::mLinkScale

protected

◆ mNumObjects

int poseNet::mNumObjects

protected

◆ mObjects

int* poseNet::mObjects

protected

◆ mPeakCounts

int* poseNet::mPeakCounts

protected

◆ mPeaks

int* poseNet::mPeaks

protected

◆ mRefinedPeaks

float* poseNet::mRefinedPeaks

protected

◆ mScoreGraph

float* poseNet::mScoreGraph

protected

◆ mThreshold

float poseNet::mThreshold

protected

◆ mTopology

Topology poseNet::mTopology

protected

◆ PAF_INTEGRAL_SAMPLES

const int poseNet::PAF_INTEGRAL_SAMPLES =7

staticprotected

Macro Definition Documentation

◆ POSENET_DEFAULT_CMAP

#define POSENET_DEFAULT_CMAP "cmap"

Name of default output blob of the confidence map for pose estimation ONNX model.

◆ POSENET_DEFAULT_INPUT

#define POSENET_DEFAULT_INPUT "input"

Name of default input blob for pose estimation ONNX model.

◆ POSENET_DEFAULT_KEYPOINT_SCALE

#define POSENET_DEFAULT_KEYPOINT_SCALE 0.0052f

Default scale used for drawing keypoint circles.

This scale is multiplied by the largest image dimension to arrive at the radius.

◆ POSENET_DEFAULT_LINK_SCALE

#define POSENET_DEFAULT_LINK_SCALE 0.0013f

Default scale used for drawing link lines.

This scale is multiplied by the largest image dimension to arrive at the line width.

◆ POSENET_DEFAULT_PAF

#define POSENET_DEFAULT_PAF "paf"

Name of default output blob of the Part Affinity Field (PAF) for pose estimation ONNX model.

◆ POSENET_DEFAULT_THRESHOLD

#define POSENET_DEFAULT_THRESHOLD 0.15f

Default value of the minimum confidence threshold.

◆ POSENET_MODEL_TYPE

#define POSENET_MODEL_TYPE "pose"

The model type for poseNet in data/networks/models.json.

Classes

Macros

Detailed Description

Class Documentation

◆ poseNet

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Static Protected Attributes

Member Enumeration Documentation

◆ OverlayFlags

Constructor & Destructor Documentation

◆ ~poseNet()

◆ poseNet()

Member Function Documentation

◆ Create() [1/4]

◆ Create() [2/4]

◆ Create() [3/4]

◆ Create() [4/4]

◆ FindKeypointID()

◆ GetCategory()

◆ GetKeypointColor()

◆ GetKeypointName()

◆ GetKeypointScale()

◆ GetLinkScale()

◆ GetNumKeypoints()

◆ GetThreshold()

◆ init()

◆ loadKeypointColors()

◆ loadTopology()

◆ Overlay() [1/2]

◆ Overlay() [2/2]

◆ OverlayFlagsFromStr()

◆ postProcess()

◆ Process() [1/4]

◆ Process() [2/4]

◆ Process() [3/4]

◆ Process() [4/4]

◆ SetKeypointAlpha() [1/2]

◆ SetKeypointAlpha() [2/2]

◆ SetKeypointColor()

◆ SetKeypointScale()

◆ SetLinkScale()

◆ SetThreshold()

◆ Usage()

Member Data Documentation

◆ CMAP_WINDOW_SIZE

◆ mAssignmentWorkspace

◆ MAX_LINKS

◆ MAX_OBJECTS

◆ mConnections

◆ mConnectionWorkspace

◆ mKeypointColors

◆ mKeypointScale

◆ mLinkScale

◆ mNumObjects

◆ mObjects

◆ mPeakCounts

◆ mPeaks

◆ mRefinedPeaks

◆ mScoreGraph

◆ mThreshold

◆ mTopology

◆ PAF_INTEGRAL_SAMPLES

Macro Definition Documentation

◆ POSENET_DEFAULT_CMAP

◆ POSENET_DEFAULT_INPUT

◆ POSENET_DEFAULT_KEYPOINT_SCALE

◆ POSENET_DEFAULT_LINK_SCALE

◆ POSENET_DEFAULT_PAF

◆ POSENET_DEFAULT_THRESHOLD

◆ POSENET_MODEL_TYPE