BodyTrackingParameters Class Reference

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

Functions
BodyTrackingParameters	__cinit__ (self, enable_tracking=True, enable_segmentation=True, detection_model=BODY_TRACKING_MODEL.HUMAN_BODY_ACCURATE, enable_body_fitting=False, max_range=-1.0, body_format=BODY_FORMAT.BODY_18, body_selection=BODY_KEYPOINTS_SELECTION.FULL, prediction_timeout_s=0.2, allow_reduced_precision_inference=False, instance_module_id=0)
	Default constructor. More...
bool	enable_tracking (self)
	Whether the body tracking system includes body/person tracking capabilities across a sequence of images. More...
bool	enable_segmentation (self)
	Whether the body/person masks will be computed. More...
BODY_TRACKING_MODEL	detection_model (self)
	sl.BODY_TRACKING_MODEL to use. More...
BODY_FORMAT	body_format (self)
	Body format to be outputted by the ZED SDK with sl.Camera.retrieve_bodies(). More...
BODY_KEYPOINTS_SELECTION	body_selection (self)
	Selection of keypoints to be outputted by the ZED SDK with sl.Camera.retrieve_bodies(). More...
bool	enable_body_fitting (self)
	Whether to apply the body fitting. More...
float	max_range (self)
	Upper depth range for detections. More...
float	prediction_timeout_s (self)
	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 (self)
	Whether to allow inference to run at a lower precision to improve runtime and memory usage. More...
int	instance_module_id (self)
	Id of the module instance. More...

Detailed Description

Class 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.

Functions

__cinit__()

BodyTrackingParameters __cinit__	(		self,
			enable_tracking = True,
			enable_segmentation = True,
			detection_model = BODY_TRACKING_MODEL.HUMAN_BODY_ACCURATE,
			enable_body_fitting = False,
			max_range = -1.0,
			body_format = BODY_FORMAT.BODY_18,
			body_selection = BODY_KEYPOINTS_SELECTION.FULL,
			prediction_timeout_s = 0.2,
			allow_reduced_precision_inference = False,
			instance_module_id = 0
	)

Default constructor.

All the parameters are set to their default values.

Parameters

enable_tracking	: Activates enable_tracking
enable_segmentation	: Activates enable_segmentation
detection_model	: Chosen detection_model
enable_body_fitting	: Activates enable_body_fitting
max_range	: Chosen max_range
body_format	: Chosen body_format
body_selection	: Chosen body_selection
prediction_timeout_s	: Chosen prediction_timeout_s
allow_reduced_precision_inference	: Activates allow_reduced_precision_inference
instance_module_id	: Chosen instance_module_id

enable_tracking()

bool enable_tracking

(

self

)

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

Default: True

enable_segmentation()

bool enable_segmentation

(

self

)

Whether the body/person masks will be computed.

Default: False

detection_model()

BODY_TRACKING_MODEL detection_model

(

self

)

sl.BODY_TRACKING_MODEL to use.

Default: sl.BODY_TRACKING_MODEL.HUMAN_BODY_ACCURATE

body_format()

BODY_FORMAT body_format

(

self

)

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

Default: sl.BODY_FORMAT.BODY_18

body_selection()

BODY_KEYPOINTS_SELECTION body_selection

(

self

)

Selection of keypoints to be outputted by the ZED SDK with sl.Camera.retrieve_bodies().

Default: sl.BODY_KEYPOINTS_SELECTION.FULL

enable_body_fitting()

bool enable_body_fitting

(

self

)

Whether to apply the body fitting.

Default: False

max_range()

float max_range

(

self

)

Upper depth range for detections.

Default: -1 (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

(

self

)

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.
Default: 0.2

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

(

self

)

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.

instance_module_id()

int instance_module_id

(

self

)

Id of the module instance.

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