#include <visp3/detection/vpDetectorDNNOpenCV.h>

Public Member Functions
	NetConfig ()

	NetConfig (const NetConfig &config)

	NetConfig (float confThresh, const float &nmsThresh, const std::vector< std::string > &classNames, const cv::Size &dnnInputSize, const double &filterSizeRatio=0., const cv::Scalar &mean=cv::Scalar(127.5, 127.5, 127.5), const double &scaleFactor=2./255., const bool &swapRB=true, const DNNResultsParsingType &parsingType=vpDetectorDNNOpenCV::USER_SPECIFIED, const std::string &modelFilename="", const std::string &configFilename="", const std::string &framework="")

	NetConfig (const float &confThresh, const float &nmsThresh, const std::string &classNamesFile, const cv::Size &dnnInputSize, const double &filterSizeRatio=0., const cv::Scalar &mean=cv::Scalar(127.5, 127.5, 127.5), const double &scaleFactor=2./255., const bool &swapRB=true, const DNNResultsParsingType &parsingType=vpDetectorDNNOpenCV::USER_SPECIFIED, const std::string &modelFilename="", const std::string &configFilename="", const std::string &framework="")

std::string	toString () const

NetConfig &	operator= (const NetConfig &config)

Static Public Member Functions
static std::vector< std::string >	parseClassNamesFile (const std::string &filename)

Public Attributes
friend	vpDetectorDNNOpenCV

Friends
void	from_json (const json &j, NetConfig &config)

void	to_json (json &j, const NetConfig &config)

std::ostream &	operator<< (std::ostream &os, const NetConfig &config)

Detailed Description

Structure containing some information required for the configuration of a vpDetectorDNNOpenCV object.

Examples: tutorial-dnn-object-detection-live.cpp, and tutorial-megapose-live-single-object-tracking.cpp.

Definition at line 177 of file vpDetectorDNNOpenCV.h.

Constructor & Destructor Documentation

◆ NetConfig() [1/4]

vpDetectorDNNOpenCV::NetConfig::NetConfig ( )

inline

Default constructor of the structure vpDetectorDNNOpenCV::NetConfig , required for JSON serialization/deserialization.

Definition at line 319 of file vpDetectorDNNOpenCV.h.

◆ NetConfig() [2/4]

vpDetectorDNNOpenCV::NetConfig::NetConfig ( const NetConfig & config )

inline

Definition at line 336 of file vpDetectorDNNOpenCV.h.

◆ NetConfig() [3/4]

vpDetectorDNNOpenCV::NetConfig::NetConfig	(	float	confThresh,
		const float &	nmsThresh,
		const std::vector< std::string > &	classNames,
		const cv::Size &	dnnInputSize,
		const double &	filterSizeRatio = `0.`,
		const cv::Scalar &	mean = `cv::Scalar(127.5, 127.5, 127.5)`,
		const double &	scaleFactor = `2. / 255.`,
		const bool &	swapRB = `true`,
		const DNNResultsParsingType &	parsingType = `vpDetectorDNNOpenCV::USER_SPECIFIED`,
		const std::string &	modelFilename = `""`,
		const std::string &	configFilename = `""`,
		const std::string &	framework = `""`
	)

inline

Construct a new Net Config object.

Parameters

confThresh	The confidence threshold to keep a detection.
nmsThresh	The Non-Maximum Suppression threshold to merge overlapping detections.
classNames	A vector containing the list of classes the DNN can detect.
dnnInputSize	The size of the input that the DNN is expecting.
filterSizeRatio	The threshold for the size filter that the user can chose to activate or not (see vpDetectorDNNOpenCV::filterDetectionSingleClassInput and vpDetectorDNNOpenCV::filterDetectionMultiClassInput methods for more information).
mean	The mean value we must deduce to each color channel of the image.
scaleFactor	The scale factor that will be multiplied to each color channel of the image.
swapRB	If true, will swap the red and blue channel of the input image.
parsingType	The type of parsing method to use to interpret the DNN raw results.
modelFilename	The path towards the DNN weights.
configFilename	The path towards the additional DNN configuration file potentially needed.
framework	The type of framework used to store the weights of the DNN.

Definition at line 370 of file vpDetectorDNNOpenCV.h.

◆ NetConfig() [4/4]

vpDetectorDNNOpenCV::NetConfig::NetConfig	(	const float &	confThresh,
		const float &	nmsThresh,
		const std::string &	classNamesFile,
		const cv::Size &	dnnInputSize,
		const double &	filterSizeRatio = `0.`,
		const cv::Scalar &	mean = `cv::Scalar(127.5, 127.5, 127.5)`,
		const double &	scaleFactor = `2. / 255.`,
		const bool &	swapRB = `true`,
		const DNNResultsParsingType &	parsingType = `vpDetectorDNNOpenCV::USER_SPECIFIED`,
		const std::string &	modelFilename = `""`,
		const std::string &	configFilename = `""`,
		const std::string &	framework = `""`
	)

inline

Construct a new Net Config object.

Parameters

confThresh	The confidence threshold to keep a detection.
nmsThresh	The Non-Maximum Suppression threshold to merge overlapping detections.
classNamesFile	The path towards the file containing the classes names, written as a YAML string array or one class name by line.
dnnInputSize	The size of the input that the DNN is expecting.
filterSizeRatio	The threshold for the size filter that the user can chose to activate or not (see vpDetectorDNNOpenCV::filterDetectionSingleClassInput and vpDetectorDNNOpenCV::filterDetectionMultiClassInput methods for more information).
mean	The mean value we must deduce to each color channel of the image.
scaleFactor	The scale factor that will be multiplied to each color channel of the image.
swapRB	If true, will swap the red and blue channel of the input image.
parsingType	The type of parsing method to use to interpret the DNN raw results.
modelFilename	The path towards the DNN weights.
configFilename	The path towards the additional DNN configuration file potentially needed.
framework	The type of framework used to store the weights of the DNN.

Definition at line 404 of file vpDetectorDNNOpenCV.h.

Member Function Documentation

◆ operator=()

NetConfig& vpDetectorDNNOpenCV::NetConfig::operator= ( const NetConfig & config )

inline

Definition at line 447 of file vpDetectorDNNOpenCV.h.

◆ parseClassNamesFile()

static std::vector<std::string> vpDetectorDNNOpenCV::NetConfig::parseClassNamesFile ( const std::string & filename )

inlinestatic

Parse the file containing the list of classes the DNN can detect. These classes can be written either as a YAML array (i.e. ["classname_0", ... ,"classname_last"]) or with one classname by row (without quotes).

For example, in the case of a yaml file called my-classes.yaml, one content could be:

$ cat my-classes.yaml
[ "person", "bicycle", "car"]

And in the case of a text file called my-classes.txt, similar content could be:

$ cat my-classes.txt
person
bicycle
car

Parameters

filename The path towards the file containing the list of classes the DNN can detect.

Returns: std::vector<std::string> The list of classes the DNN can detect.

Definition at line 286 of file vpDetectorDNNOpenCV.h.

Referenced by vpDetectorDNNOpenCV::parseClassNamesFile().

◆ toString()

std::string vpDetectorDNNOpenCV::NetConfig::toString ( ) const

inline

Definition at line 422 of file vpDetectorDNNOpenCV.h.

References vpDetectorDNNOpenCV::dnnResultsParsingTypeToString().

Friends And Related Function Documentation

◆ from_json

void from_json	(	const json &	j,
		NetConfig &	config
	)

friend

Read the network configuration from JSON. All values are optional and if an argument is not present, the default value defined in the constructor is kept.

Parameters

j	The JSON object, resulting from the parsing of a JSON file.
config	The configuration of the network, that will be initialized from the JSON data.

Definition at line 202 of file vpDetectorDNNOpenCV.h.

◆ operator<<

std::ostream& operator<<	(	std::ostream &	os,
		const NetConfig &	config
	)

friend

Definition at line 441 of file vpDetectorDNNOpenCV.h.

◆ to_json

void to_json	(	json &	j,
		const NetConfig &	config
	)

friend

Parse a vpDetectorDNNOpenCV::NetConfig into JSON format.

Parameters

j	A JSON parser object.
config	The vpDetectorDNNOpenCV::NetConfig that must be parsed into JSON format.

Definition at line 242 of file vpDetectorDNNOpenCV.h.

Member Data Documentation

◆ vpDetectorDNNOpenCV

friend vpDetectorDNNOpenCV::NetConfig::vpDetectorDNNOpenCV

Definition at line 464 of file vpDetectorDNNOpenCV.h.

Public Member Functions

Static Public Member Functions

Public Attributes

Friends

Detailed Description

Constructor & Destructor Documentation

◆ NetConfig() [1/4]

◆ NetConfig() [2/4]

◆ NetConfig() [3/4]

◆ NetConfig() [4/4]

Member Function Documentation

◆ operator=()

◆ parseClassNamesFile()

◆ toString()

Friends And Related Function Documentation

◆ from_json

◆ operator<<

◆ to_json

Member Data Documentation

◆ vpDetectorDNNOpenCV