Structure containing a set of parameters for the body tracking module. More...

Functions
	BodyTrackingParameters (bool enable_tracking_=true, bool enable_segmentation_=false, BODY_TRACKING_MODEL detection_model=BODY_TRACKING_MODEL::HUMAN_BODY_ACCURATE, bool enable_body_fitting_=false, float max_range_=-1.f, BODY_FORMAT body_format_=BODY_FORMAT::BODY_18, BODY_KEYPOINTS_SELECTION body_selection=BODY_KEYPOINTS_SELECTION::FULL, float prediction_timeout_s=0.2f, bool allow_reduced_precision_inference=false, unsigned int instance_id=0)
	Default constructor. More...

bool	save (String filename) const
	Saves the current set of parameters into a file to be reloaded with the load() method. More...

bool	load (String filename)
	Loads a set of parameters from the values contained in a previously saved file. More...

bool	encode (String &serialized_content) const
	Generate a JSON Object (with the struct type as a key) containing the serialized struct, converted into a string. More...

bool	decode (const String &serialized_content)
	Fill the structure from the serialized json object contained in the input string. More...

bool	operator== (const BodyTrackingParameters &param1) const

bool	operator!= (const BodyTrackingParameters &param1) const

Attributes
unsigned int	instance_module_id = 0
	Id of the module instance. More...

bool	enable_tracking = true
	Whether the body tracking system includes body/person tracking capabilities across a sequence of images. More...

bool	enable_segmentation = false
	Whether the body/person masks will be computed. More...

BODY_TRACKING_MODEL	detection_model = BODY_TRACKING_MODEL::HUMAN_BODY_ACCURATE
	sl::BODY_TRACKING_MODEL to use. More...

bool	enable_body_fitting = false
	Whether to apply the body fitting. More...

BODY_FORMAT	body_format = BODY_FORMAT::BODY_18
	Body format to be outputted by the ZED SDK with sl::Camera.retrieveBodies(). More...

BODY_KEYPOINTS_SELECTION	body_selection = BODY_KEYPOINTS_SELECTION::FULL
	Selection of keypoints to outputted by the ZED SDK with sl::Camera.retrieveBodies(). More...

float	max_range = -1.f
	Upper depth range for detections. More...

float	prediction_timeout_s
	Prediction duration of the ZED SDK when an object is not detected anymore before switching its state to sl::OBJECT_TRACKING_STATE::SEARCHING. More...

bool	allow_reduced_precision_inference
	Whether to allow inference to run at a lower precision to improve runtime and memory usage. More...

Detailed Description

Structure containing a set of parameters for the body tracking module.

The default constructor sets all parameters to their default settings.

Note: Parameters can be adjusted by the user.

Constructor and Destructor

◆ BodyTrackingParameters()

BodyTrackingParameters	(	bool	enable_tracking_ = `true`,
		bool	enable_segmentation_ = `false`,
		BODY_TRACKING_MODEL	detection_model = `BODY_TRACKING_MODEL::HUMAN_BODY_ACCURATE`,
		bool	enable_body_fitting_ = `false`,
		float	max_range_ = `-1.f`,
		BODY_FORMAT	body_format_ = `BODY_FORMAT::BODY_18`,
		BODY_KEYPOINTS_SELECTION	body_selection = `BODY_KEYPOINTS_SELECTION::FULL`,
		float	prediction_timeout_s = `0.2f`,
		bool	allow_reduced_precision_inference = `false`,
		unsigned int	instance_id = `0`
	)

Default constructor.

All the parameters are set to their default values.

Functions

◆ save()

bool save ( String filename ) const

Saves the current set of parameters into a file to be reloaded with the load() method.

Parameters

filename : Name of the file which will be created to store the parameters (extension '.json' will be added if not set).

Returns: True if the file was successfully saved, otherwise false.

Warning: For security reasons, the file must not already exist.; In case a file already exists, the method will return false and existing file will not be updated.

◆ load()

bool load ( String filename )

Loads a set of parameters from the values contained in a previously saved file.

Parameters

filename : Path to the file from which the parameters will be loaded (extension '.json' will be added at the end of the filename if not detected).

Returns: True if the file was successfully loaded, otherwise false.

◆ encode()

bool encode ( String & serialized_content ) const

Generate a JSON Object (with the struct type as a key) containing the serialized struct, converted into a string.

Parameters

serialized_content output string containing the JSON Object

Returns: True if file was successfully saved, otherwise false.

◆ decode()

bool decode ( const String & serialized_content )

Fill the structure from the serialized json object contained in the input string.

Parameters

serialized_content input string containing the JSON Object

Returns: True if the decoding was successful, otherwise false.

◆ operator==()

bool operator== ( const BodyTrackingParameters & param1 ) const

Comparison operator ==

Parameters

param1 to compare

Returns: true if the two struct are identical

◆ operator!=()

bool operator!= ( const BodyTrackingParameters & param1 ) const

Comparison operator !=

Parameters

param1 to compare

Returns: true if the two struct are different

Variables

◆ instance_module_id

unsigned int instance_module_id = 0

Id of the module instance.

This is used to identify which body tracking module instance is used.

◆ enable_tracking

bool enable_tracking = true

Whether the body tracking system includes body/person tracking capabilities across a sequence of images.

◆ enable_segmentation

bool enable_segmentation = false

Whether the body/person masks will be computed.

◆ detection_model

BODY_TRACKING_MODEL detection_model = BODY_TRACKING_MODEL::HUMAN_BODY_ACCURATE

sl::BODY_TRACKING_MODEL to use.

◆ enable_body_fitting

bool enable_body_fitting = false

Whether to apply the body fitting.

◆ body_format

BODY_FORMAT body_format = BODY_FORMAT::BODY_18

Body format to be outputted by the ZED SDK with sl::Camera.retrieveBodies().

◆ body_selection

BODY_KEYPOINTS_SELECTION body_selection = BODY_KEYPOINTS_SELECTION::FULL

Selection of keypoints to outputted by the ZED SDK with sl::Camera.retrieveBodies().

◆ max_range

float max_range = -1.f

Upper depth range for detections.

Default: -1.f (value set in sl::InitParameters.depth_maximum_distance)

Note: The value cannot be greater than sl::InitParameters.depth_maximum_distance and its unit is defined in sl::InitParameters.coordinate_units.

◆ prediction_timeout_s

float prediction_timeout_s

Prediction duration of the ZED SDK when an object is not detected anymore before switching its state to sl::OBJECT_TRACKING_STATE::SEARCHING.

It prevents the jittering of the object state when there is a short misdetection.
The user can define their own prediction time duration.

Note: During this time, the object will have sl::OBJECT_TRACKING_STATE::OK state even if it is not detected.; The duration is expressed in seconds.

Warning: prediction_timeout_s will be clamped to 1 second as the prediction is getting worse with time.; Setting this parameter to 0 disables the ZED SDK predictions.

◆ allow_reduced_precision_inference

bool allow_reduced_precision_inference

Whether to allow inference to run at a lower precision to improve runtime and memory usage.

It might increase the initial optimization time and could include downloading calibration data or calibration cache and slightly reduce the accuracy.

Note: The fp16 is automatically enabled if the GPU is compatible and provides a speed up of almost x2 and reduce memory usage by almost half, no precision loss.; This setting allow int8 precision which can speed up by another x2 factor (compared to fp16, or x4 compared to fp32) and half the fp16 memory usage, however some accuracy could be lost.; The accuracy loss should not exceed 1-2% on the compatible models.; The current compatible models are all sl::AI_MODELS::HUMAN_BODY_XXXX.

Functions

Attributes

Detailed Description

Constructor and Destructor

◆ BodyTrackingParameters()

Functions

◆ save()

◆ load()

◆ encode()

◆ decode()

◆ operator==()

◆ operator!=()

Variables

◆ instance_module_id

◆ enable_tracking

◆ enable_segmentation

◆ detection_model

◆ enable_body_fitting

◆ body_format

◆ body_selection

◆ max_range

◆ prediction_timeout_s

◆ allow_reduced_precision_inference