Object Detection Module

Classes
struct	BatchParameters
	Structure containing a set of parameters for batch object detection. More...
struct	ObjectDetectionParameters
	Structure containing a set of parameters for the object detection module. More...
struct	ObjectTrackingParameters
	Structure containing a set of parameters for the object tracking module. More...
struct	ObjectDetectionRuntimeParameters
	Structure containing a set of runtime parameters for the object detection module. More...
struct	ObjectData
	Structure containing data of a detected object such as its boundingBox, label, id and its 3D position. More...
struct	CustomBoxObjectData
	Structure that store externally detected objects. More...
struct	Objects
	Structure containing the results of the object detection module. It contains the number of object in the scene (numObject) and the objectData structure for each object. More...
class	ObjectsBatch
	Class containing batched data of a detected objects from the object detection module. More...

Enumerations
enum class	OBJECT_ACCELERATION_PRESET
	Lists of supported presets for maximum acceleration allowed for a given tracked object. More...
enum class	OBJECT_CLASS
	Lists available object classes. More...
enum class	OBJECT_SUBCLASS
	List available object subclasses. More...
enum class	OBJECT_TRACKING_STATE
	Lists the different states of object tracking. More...
enum class	OBJECT_ACTION_STATE
	Lists the different states of an object's actions. More...
enum class	OBJECT_DETECTION_MODEL
	Lists available models for the object detection module. More...

Enumeration Type Documentation

OBJECT_ACCELERATION_PRESET

enum OBJECT_ACCELERATION_PRESET

strong

Lists of supported presets for maximum acceleration allowed for a given tracked object.

Enumerator
DEFAULT	The ZED SDK will automatically determine the appropriate maximum acceleration.
LOW	Suitable for objects with relatively low maximum acceleration (e.g., a person walking).
MEDIUM	Suitable for objects with moderate maximum acceleration (e.g., a person running).
HIGH	Suitable for objects with high maximum acceleration (e.g., a car accelerating, a kicked sports ball).

OBJECT_CLASS

enum OBJECT_CLASS

strong

Lists available object classes.

Enumerator
PERSON	For people detection
VEHICLE	For vehicle detection (cars, trucks, buses, motorcycles, etc.)
BAG	For bag detection (backpack, handbag, suitcase, etc.)
ANIMAL	For animal detection (cow, sheep, horse, dog, cat, bird, etc.)
ELECTRONICS	For electronic device detection (cellphone, laptop, etc.)
FRUIT_VEGETABLE	For fruit and vegetable detection (banana, apple, orange, carrot, etc.)
SPORT	For sport-related object detection (sport ball, etc.)

OBJECT_SUBCLASS

enum OBJECT_SUBCLASS

strong

List available object subclasses.

Given as hint, when using object tracking an object can change of sl.OBJECT_SUBCLASS while keeping the same sl.OBJECT_CLASS (i.e.: frame n: sl.OBJECT_SUBCLASS.MOTORBIKE, frame n+1: sl.OBJECT_SUBCLASS.BICYCLE).

Enumerator
PERSON	sl.OBJECT_CLASS.PERSON
BICYCLE	sl.OBJECT_CLASS.VEHICLE
CAR	sl.OBJECT_CLASS.VEHICLE
MOTORBIKE	sl.OBJECT_CLASS.VEHICLE
BUS	sl.OBJECT_CLASS.VEHICLE
TRUCK	sl.OBJECT_CLASS.VEHICLE
BOAT	sl.OBJECT_CLASS.VEHICLE
BACKPACK	sl.OBJECT_CLASS.BAG
HANDBAG	sl.OBJECT_CLASS.BAG
SUITCASE	sl.OBJECT_CLASS.BAG
BIRD	sl.OBJECT_CLASS.ANIMAL
CAT	sl.OBJECT_CLASS.ANIMAL
DOG	sl.OBJECT_CLASS.ANIMAL
HORSE	sl.OBJECT_CLASS.ANIMAL
SHEEP	sl.OBJECT_CLASS.ANIMAL
COW	sl.OBJECT_CLASS.ANIMAL
CELLPHONE	sl.OBJECT_CLASS.ELECTRONICS
LAPTOP	sl.OBJECT_CLASS.ELECTRONICS
BANANA	sl.OBJECT_CLASS.FRUIT_VEGETABLE
APPLE	sl.OBJECT_CLASS.FRUIT_VEGETABLE
ORANGE	sl.OBJECT_CLASS.FRUIT_VEGETABLE
CARROT	sl.OBJECT_CLASS.FRUIT_VEGETABLE
PERSON_HEAD	sl.OBJECT_CLASS.PERSON
SPORTSBALL	sl.OBJECT_CLASS.SPORT
MACHINERY	sl.OBJECT_CLASS.VEHICLE

OBJECT_TRACKING_STATE

enum OBJECT_TRACKING_STATE

strong

Lists the different states of object tracking.

Enumerator
OFF	The tracking is not yet initialized. The object id is not usable.
OK	The object is tracked.
SEARCHING	The object could not be detected in the image and is potentially occluded. The trajectory is estimated.
TERMINATE	This is the last searching state of the track. The track will be deleted in the next sl.Camera.RetrieveObjects().

OBJECT_ACTION_STATE

enum OBJECT_ACTION_STATE

strong

Lists the different states of an object's actions.

Enumerator
IDLE	The object is staying static.
MOVING	The object is moving.

OBJECT_DETECTION_MODEL

enum OBJECT_DETECTION_MODEL

strong

Lists available models for the object detection module.

Enumerator
MULTI_CLASS_BOX_FAST	Any objects, bounding box based.
MULTI_CLASS_BOX_MEDIUM	Any objects, bounding box based, compromise between accuracy and speed.
MULTI_CLASS_BOX_ACCURATE	Any objects, bounding box based, more accurate but slower than the base model.
PERSON_HEAD_BOX_FAST	Bounding box detector specialized in person heads particularly well suited for crowded environments. The person localization is also improved.
PERSON_HEAD_BOX_ACCURATE	Bounding box detector specialized in person heads, particularly well suited for crowded environments. The person localization is also improved, more accurate but slower than the base model.
CUSTOM_BOX_OBJECTS	For external inference, using your own custom model and/or frameworks. This mode disables the internal inference engine, the 2D bounding box detection must be provided.
CUSTOM_YOLOLIKE_BOX_OBJECTS	For internal inference using your own custom YOLO-like model. Requires an ONNX file in the detection parameters.
CUSTOM_RFDETRLIKE_BOX_OBJECTS	For internal inference using your own custom RF-DETR / DETR-like model (two outputs: boxes + class logits, NMS-free). Requires an ONNX file.
CUSTOM_BOX_OBJECTS_AUTODETECT	For internal inference using your own custom ONNX model, auto-detecting YOLO-like vs RF-DETR/DETR-like from the model outputs. Requires an ONNX file.