Container to store the externally detected objects. The objects can be ingested using Camera::ingestcustomBoxObjects() functions to extract 3D information and tracking over time. More...

Functions
	CustomBoxObjectData ()

Attributes
String	unique_object_id
	Unique ID to help identify and track AI detections. Can be either generated externally, or using generate_unique_id() or left empty. More...

std::vector< sl::uint2 >	bounding_box_2d
	2D bounding box represented as four 2D points starting at the top left corner and rotation clockwise. Expressed in pixels on the original image resolution, [0,0] is the top left corner. More...

int	label
	Object label, this information is passed-through and can be used to improve object tracking Should define an object class. This means that any similar object (in classification) should share the same label number. More...

float	probability
	Detection confidence. Should be [0-1]. It can be used to improve the object tracking. More...

bool	is_grounded = true
	Provide hypothesis about the object movements (degrees of freedom) to improve the object tracking. More...

Detailed Description

Container to store the externally detected objects. The objects can be ingested using Camera::ingestcustomBoxObjects() functions to extract 3D information and tracking over time.

Constructor and Destructor

◆ CustomBoxObjectData()

CustomBoxObjectData ( )

Variables

◆ unique_object_id

String unique_object_id

Unique ID to help identify and track AI detections. Can be either generated externally, or using generate_unique_id() or left empty.

◆ bounding_box_2d

std::vector<sl::uint2> bounding_box_2d

2D bounding box represented as four 2D points starting at the top left corner and rotation clockwise. Expressed in pixels on the original image resolution, [0,0] is the top left corner.

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

◆ label

int label

Object label, this information is passed-through and can be used to improve object tracking Should define an object class. This means that any similar object (in classification) should share the same label number.

◆ probability

float probability

Detection confidence. Should be [0-1]. It can be used to improve the object tracking.

◆ is_grounded

bool is_grounded = true

Provide hypothesis about the object movements (degrees of freedom) to improve the object tracking.

true: means 2 DoF projected alongside the floor plane, the default for object standing on the ground such as person, vehicle, etc. The projection implies that the objects can't be superposed on multiple horizontal levels
false: 6 DoF full 3D movements are allowed

Note: This parameter can't be changed for a given object tracking ID, it's advises to set it by labels to avoid issues.

Functions

Attributes