BodiesBatch Class Reference

Class containing batched data of a detected bodies/persons from the body tracking module. More...

Functions
int	id (self)
	Id of the batch.
OBJECT_TRACKING_STATE	tracking_state (self)
	Bodies/persons tracking state.
np.array[float][float]	positions (self)
	NumPy array of positions for each body/person.
np.array[float][float]	position_covariances (self)
	NumPy array of positions' covariances for each body/person.
np.array[float][float]	velocities (self)
	NumPy array of 3D velocities for each body/person.
list[Timestamp]	timestamps (self)
	List of timestamps for each body/person.
np.array[float][float][float]	bounding_boxes (self)
	NumPy array of 3D bounding boxes for each body/person. More...
np.array[int][int][int]	bounding_boxes_2d (self)
	NumPy array of 2D bounding boxes for each body/person. More...
np.array[float]	confidences (self)
	NumPy array of confidences for each body/person.
list[OBJECT_ACTION_STATE]	action_states (self)
	List of action states for each body/person.
np.array[int][int][int]	keypoints_2d (self)
	NumPy array of 2D keypoints for each body/person. More...
np.array[int][int][int]	head_bounding_boxes_2d (self)
	NumPy array of 2D bounding box of the head for each body/person. More...
np.array[float][float][float]	head_bounding_boxes (self)
	NumPy array of 3D bounding box of the head for each body/person. More...
np.array[float][float]	head_positions (self)
	NumPy array of 3D centroid of the head for each body/person. More...

Detailed Description

Class containing batched data of a detected bodies/persons from the body tracking module.

Functions

bounding_boxes()

np.array[float][float][float] bounding_boxes

(

self

)

NumPy array of 3D bounding boxes for each body/person.

Note

They are defined in sl.InitParameters.coordinate_units and expressed in sl.RuntimeParameters.measure3D_reference_frame.

  1 ------ 2
 /        /|
0 ------ 3 |
| Object | 6
|        |/
4 ------ 7

bounding_boxes_2d()

np.array[int][int][int] bounding_boxes_2d

(

self

)

NumPy array of 2D bounding boxes for each body/person.

Note

Expressed in pixels on the original image resolution, [0, 0] is the top left corner.

A ------ B
| Object |
D ------ C

keypoints_2d()

np.array[int][int][int] keypoints_2d

(

self

)

NumPy array of 2D keypoints for each body/person.

Warning

In some cases, eg. body partially out of the image or missing depth data, some keypoints can not be detected. They will have non finite values.

NumPy array of 3D keypoints for each body/person.

Warning

In some cases, eg. body partially out of the image or missing depth data, some keypoints can not be detected. They will have non finite values.

head_bounding_boxes_2d()

np.array[int][int][int] head_bounding_boxes_2d

(

self

)

NumPy array of 2D bounding box of the head for each body/person.

Note

Expressed in pixels on the original image resolution, [0, 0] is the top left corner.

head_bounding_boxes()

np.array[float][float][float] head_bounding_boxes

(

self

)

NumPy array of 3D bounding box of the head for each body/person.

Note

They are defined in sl.InitParameters.coordinate_units and expressed in sl.RuntimeParameters.measure3D_reference_frame.

head_positions()

np.array[float][float] head_positions

(

self

)

NumPy array of 3D centroid of the head for each body/person.

Note

They are defined in sl.InitParameters.coordinate_units and expressed in sl.RuntimeParameters.measure3D_reference_frame.

NumPy array of detection confidences NumPy array for each keypoint for each body/person.

Note

They can not be lower than the sl.BodyTrackingRuntimeParameters.detection_confidence_threshold.

Warning

In some cases, eg. body partially out of the image or missing depth data, some keypoints can not be detected. They will have non finite values.