ObjectsBatch Class Reference

Class containing batched data of a detected objects from the object detection module. More...

Attributes
int	numData = 0
	Number of objects in the sl.ObjectsBatch. More...
int	id = 0
	Id of the batch. More...
OBJECT_CLASS	label = OBJECT_CLASS.LAST
	Objects class/category to identify the object type. More...
OBJECT_SUBCLASS	sublabel = OBJECT_SUBCLASS.LAST
	Objects sub-class/sub-category to identify the object type. More...
OBJECT_TRACKING_STATE	trackingState = OBJECT_TRACKING_STATE.TERMINATE
	Objects tracking state. More...
Vector3[]	positions = new Vector3[(int)Constant.MAX_BATCH_SIZE]
	Array of positions for each object. More...
float[,]	positionCovariances = new float[(int)Constant.MAX_BATCH_SIZE, 6]
	Array of positions' covariances for each object. More...
Vector3[]	velocities = new Vector3[(int)Constant.MAX_BATCH_SIZE]
	Array of 3D velocities for each object. More...
ulong[]	timestamps = new ulong[(int)Constant.MAX_BATCH_SIZE]
	Array of timestamps for each object. More...
Vector3[,]	boundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8]
	Array of 3D bounding boxes for each object. More...
Vector2[,]	boundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 4]
	Array of 2D bounding boxes for each object. More...
float[]	confidences = new float[(int)Constant.MAX_BATCH_SIZE]
	Array of confidences for each object. More...
OBJECT_ACTION_STATE[]	actionStates = new OBJECT_ACTION_STATE[(int)Constant.MAX_BATCH_SIZE]
	Array of action states for each object. More...
Vector2[,]	headBoundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 8]
	Array of 2D bounding box of the head for each object (person). More...
Vector3[,]	headBoundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8]
	Array of 3D bounding box of the head for each object (person). More...
Vector3[]	headPositions = new Vector3[(int)Constant.MAX_BATCH_SIZE]
	Array of 3D centroid of the head for each object (person). More...

Detailed Description

Class containing batched data of a detected objects from the object detection module.

This class can be used to store trajectories.

Variables

numData

int numData = 0

Number of objects in the sl.ObjectsBatch.

Use this to iterate through the top of positions / velocities / boundingBoxes / etc.

Note

Objects with greater indexes are empty.

id

int id = 0

Id of the batch.

label

OBJECT_CLASS label = OBJECT_CLASS.LAST

Objects class/category to identify the object type.

sublabel

OBJECT_SUBCLASS sublabel = OBJECT_SUBCLASS.LAST

Objects sub-class/sub-category to identify the object type.

trackingState

OBJECT_TRACKING_STATE trackingState = OBJECT_TRACKING_STATE.TERMINATE

Objects tracking state.

positions

Vector3 [] positions = new Vector3[(int)Constant.MAX_BATCH_SIZE]

Array of positions for each object.

positionCovariances

float [,] positionCovariances = new float[(int)Constant.MAX_BATCH_SIZE, 6]

Array of positions' covariances for each object.

velocities

Vector3 [] velocities = new Vector3[(int)Constant.MAX_BATCH_SIZE]

Array of 3D velocities for each object.

timestamps

ulong [] timestamps = new ulong[(int)Constant.MAX_BATCH_SIZE]

Array of timestamps for each object.

boundingBoxes

Vector3 [,] boundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8]

Array of 3D bounding boxes for each object.

Note

They are defined in sl.InitParameters.coordinateUnits and expressed in sl.RuntimeParameters.measure3DReferenceFrame.

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

boundingBoxes2D

Vector2 [,] boundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 4]

Array of 2D bounding boxes for each object.

Note

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

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

confidences

float [] confidences = new float[(int)Constant.MAX_BATCH_SIZE]

Array of confidences for each object.

actionStates

OBJECT_ACTION_STATE [] actionStates = new OBJECT_ACTION_STATE[(int)Constant.MAX_BATCH_SIZE]

Array of action states for each object.

headBoundingBoxes2D

Vector2 [,] headBoundingBoxes2D = new Vector2[(int)Constant.MAX_BATCH_SIZE, 8]

Array of 2D bounding box of the head for each object (person).

Note

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

Warning

Not available with sl.OBJECT_DETECTION_MODEL.MULTI_CLASS_BOX_XXX.

headBoundingBoxes

Vector3 [,] headBoundingBoxes = new Vector3[(int)Constant.MAX_BATCH_SIZE, 8]

Array of 3D bounding box of the head for each object (person).

Note

They are defined in sl.InitParameters.coordinateUnits and expressed in sl.RuntimeParameters.measure3DReferenceFrame.

Warning

Not available with sl.OBJECT_DETECTION_MODEL.MULTI_CLASS_BOX_XXX.

headPositions

Vector3 [] headPositions = new Vector3[(int)Constant.MAX_BATCH_SIZE]

Array of 3D centroid of the head for each object (person).

Note

They are defined in sl.InitParameters.coordinateUnits and expressed in sl.RuntimeParameters.measure3DReferenceFrame.

Warning

Not available with sl.OBJECT_DETECTION_MODEL.MULTI_CLASS_BOX_XXX.