This class represents region of interest - object describing detection result (bounding box) and containing multiple Tensor objects (inference results) attached by multiple models. For example, it can be region of interest with detected face and recognized age and sex of a person. It can be produced by a pipeline with gvadetect with detection model and two gvaclassify elements with two classification models. Such RegionOfInterest will have bounding box coordinates filled and will have 3 Tensor objects attached - 1 Tensor object with detection result and 2 Tensor objects with classification results coming from 2 classifications. More...

#include <region_of_interest.h>

Collaboration diagram for GVA::RegionOfInterest:

[legend]

Public Member Functions
Rect< uint32_t >	rect () const
	Get bounding box of the RegionOfInterest as pixel coordinates in original image. More...

Rect< double >	normalized_rect ()
	Get bounding box of the RegionOfInterest as normalized coordinates in the range [0, 1]. More...

std::string	label () const
	Get RegionOfInterest label. More...

double	confidence () const
	Get RegionOfInterest detection confidence (set by gvadetect) More...

int32_t	object_id () const
	Get unique id of the RegionOfInterest. The id typically created by gvatrack element. More...

std::vector< Tensor >	tensors () const
	Get all Tensor instances added to this RegionOfInterest. More...

Tensor	add_tensor (const std::string &name)
	Add new tensor (inference result) to this RegionOfInterest with name set. To add detection tensor, set name to "detection". More...

Tensor	detection ()
	Returns detection Tensor, last added to this RegionOfInterest. As any other Tensor, returned detection Tensor can contain arbitrary information. If you use RegionOfInterest based on GstVideoRegionOfInterestMeta attached by gvadetect by default, then this Tensor will contain "label_id", "confidence", "x_min", "x_max", "y_min", "y_max" fields. If RegionOfInterest doesn't have detection Tensor, it will be created in-place. More...

int	label_id () const
	Get label_id from detection Tensor, last added to this RegionOfInterest. More...

	RegionOfInterest (GstVideoRegionOfInterestMeta *meta)
	Construct RegionOfInterest instance from GstVideoRegionOfInterestMeta. After this, RegionOfInterest will obtain all tensors (detection & inference results) from GstVideoRegionOfInterestMeta. More...

void	set_label (std::string label)
	Set RegionOfInterest label. More...

void	set_object_id (int32_t id)
	Set object ID. More...

GstVideoRegionOfInterestMeta *	_meta () const
	Internal function, don't use or use with caution. More...

Protected Attributes
GstVideoRegionOfInterestMeta *	_gst_meta
	GstVideoRegionOfInterestMeta containing fields filled with detection result (produced by gvadetect element in Gstreamer pipeline) and all the additional tensors, describing detection and other inference results (produced by gvainference, gvadetect, gvaclassify in Gstreamer pipeline)

std::vector< Tensor >	_tensors
	vector of Tensor objects added to this RegionOfInterest (describing detection & inference results), obtained from GstVideoRegionOfInterestMeta

Tensor *	_detection
	last added detection Tensor instance, defined as Tensor with name set to "detection"

Detailed Description

This class represents region of interest - object describing detection result (bounding box) and containing multiple Tensor objects (inference results) attached by multiple models. For example, it can be region of interest with detected face and recognized age and sex of a person. It can be produced by a pipeline with gvadetect with detection model and two gvaclassify elements with two classification models. Such RegionOfInterest will have bounding box coordinates filled and will have 3 Tensor objects attached - 1 Tensor object with detection result and 2 Tensor objects with classification results coming from 2 classifications.

Constructor & Destructor Documentation

◆ RegionOfInterest()

GVA::RegionOfInterest::RegionOfInterest ( GstVideoRegionOfInterestMeta * meta )

inline

Construct RegionOfInterest instance from GstVideoRegionOfInterestMeta. After this, RegionOfInterest will obtain all tensors (detection & inference results) from GstVideoRegionOfInterestMeta.

Parameters

meta	GstVideoRegionOfInterestMeta containing bounding box information and tensors

Member Function Documentation

◆ _meta()

GstVideoRegionOfInterestMeta* GVA::RegionOfInterest::_meta ( ) const

inline

Internal function, don't use or use with caution.

Returns: pointer to underlying GstVideoRegionOfInterestMeta

◆ add_tensor()

Tensor GVA::RegionOfInterest::add_tensor ( const std::string & name )

inline

Add new tensor (inference result) to this RegionOfInterest with name set. To add detection tensor, set name to "detection".

Parameters

name	name for the tensor. If name is set to "detection", detection Tensor will be created and set for this RegionOfInterest

Returns: just created Tensor object, which can be filled with tensor information further

◆ confidence()

double GVA::RegionOfInterest::confidence ( ) const

inline

Get RegionOfInterest detection confidence (set by gvadetect)

Returns: last added detection Tensor confidence if exists, otherwise 0.0

◆ detection()

Tensor GVA::RegionOfInterest::detection ( )

inline

Returns detection Tensor, last added to this RegionOfInterest. As any other Tensor, returned detection Tensor can contain arbitrary information. If you use RegionOfInterest based on GstVideoRegionOfInterestMeta attached by gvadetect by default, then this Tensor will contain "label_id", "confidence", "x_min", "x_max", "y_min", "y_max" fields. If RegionOfInterest doesn't have detection Tensor, it will be created in-place.

Returns: detection Tensor, empty if there were no detection Tensor objects added to this RegionOfInterest when this method was called

◆ label()

std::string GVA::RegionOfInterest::label ( ) const

inline

Get RegionOfInterest label.

Returns: RegionOfInterest label

◆ label_id()

int GVA::RegionOfInterest::label_id ( ) const

inline

Get label_id from detection Tensor, last added to this RegionOfInterest.

Returns: last added detection Tensor label_id if exists, otherwise 0

◆ normalized_rect()

Rect<double> GVA::RegionOfInterest::normalized_rect ( )

inline

Get bounding box of the RegionOfInterest as normalized coordinates in the range [0, 1].

Returns: Bounding box coordinates of the RegionOfInterest

◆ object_id()

int32_t GVA::RegionOfInterest::object_id ( ) const

inline

Get unique id of the RegionOfInterest. The id typically created by gvatrack element.

Returns: Unique id, or zero value if not found

◆ rect()

Rect<uint32_t> GVA::RegionOfInterest::rect ( ) const

inline

Get bounding box of the RegionOfInterest as pixel coordinates in original image.

Returns: Bounding box coordinates of the RegionOfInterest

◆ set_label()

void GVA::RegionOfInterest::set_label ( std::string label )

inline

Set RegionOfInterest label.

Parameters

label Label to set

◆ set_object_id()

void GVA::RegionOfInterest::set_object_id ( int32_t id )

inline

Set object ID.

Parameters

id ID to set

◆ tensors()

std::vector<Tensor> GVA::RegionOfInterest::tensors ( ) const

inline

Get all Tensor instances added to this RegionOfInterest.

Returns: vector of Tensor instances added to this RegionOfInterest

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

/home/gst-libs/gst/videoanalytics/region_of_interest.h

Public Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ RegionOfInterest()

Member Function Documentation

◆ _meta()

◆ add_tensor()

◆ confidence()

◆ detection()

◆ label()

◆ label_id()

◆ normalized_rect()

◆ object_id()

◆ rect()

◆ set_label()

◆ set_object_id()

◆ tensors()