Object Detection Module

Classes

struct  BatchParameters
 sets batch trajectory parameters The default constructor sets all parameters to their default settings. Parameters can be user adjusted. More...
 
struct  ObjectDetectionParameters
 Sets the object detection parameters. More...
 
struct  ObjectDetectionRuntimeParameters
 Sets the object detection runtime parameters. More...
 
struct  ObjectData
 Object data structure directly from the SDK. Represents a single object detection. More...
 
struct  CustomBoxObjectData
 Container to store the externally detected objects. The objects can be ingested using IngestCustomBoxObjects() function to extract 3D information and tracking over time. More...
 
struct  Objects
 Object Scene data directly from the ZED SDK. Represents all detections given during a single image frame. Contains the number of object in the scene and the objectData structure for each object. Since the data is transmitted from C++ to C#, the size of the structure must be constant. Therefore, there is a limitation of 200 (MAX_OBJECT constant) objects in the image. More...
 
class  ObjectsBatch
 Contains batched data of a detected object More...
 

Enumerations

enum class  BODY_FORMAT
 Lists of supported skeleton body model More...
 
enum class  OBJECT_CLASS
 Lists available object class More...
 
enum class  OBJECT_SUBCLASS
 Lists available object subclass. More...
 
enum class  OBJECT_TRACKING_STATE
 Tracking state of an individual object. More...
 
enum class  OBJECT_ACTION_STATE
 Lists available object action state. More...
 
enum class  DETECTION_MODEL
 List available models for detection More...
 
enum class  BODY_PARTS
 semantic and order of human body keypoints. More...
 
enum class  BODY_PARTS_POSE_34
 ssemantic of human body parts and order keypoints for BODY_FORMAT.POSE_34. More...
 

Enumeration Type Documentation

◆ BODY_FORMAT

enum BODY_FORMAT
strong

Lists of supported skeleton body model

Enumerator
POSE_18 
POSE_34 

◆ OBJECT_CLASS

enum OBJECT_CLASS
strong

Lists available object class

Enumerator
PERSON 
VEHICLE 
BAG 
ANIMAL 
ELECTRONICS 
FRUIT_VEGETABLE 
SPORT 
LAST 

◆ OBJECT_SUBCLASS

enum OBJECT_SUBCLASS
strong

Lists available object subclass.

Enumerator
PERSON 
BICYCLE 
CAR 
MOTORBIKE 
BUS 
TRUCK 
BOAT 
BACKPACK 
HANDBAG 
SUITCASE 
BIRD 
CAT 
DOG 
HORSE 
SHEEP 
COW 
CELLPHONE 
LAPTOP 
BANANA 
APPLE 
ORANGE 
CARROT 
PERSON_HEAD 
SPORTSBALL 
LAST 

◆ OBJECT_TRACKING_STATE

enum OBJECT_TRACKING_STATE
strong

Tracking state of an individual object.

Enumerator
OFF 

The tracking is not yet initialized, the object ID is not usable.

OK 

The object is tracked.

SEARCHING 

The object couldn't 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 retreiveObject.

◆ OBJECT_ACTION_STATE

enum OBJECT_ACTION_STATE
strong

Lists available object action state.

Enumerator
IDLE 

The object is staying static.

MOVING 

The object is moving.

◆ DETECTION_MODEL

enum DETECTION_MODEL
strong

List available models for detection

Enumerator
MULTI_CLASS_BOX 

Any objects, bounding box based.

MULTI_CLASS_BOX_ACCURATE 

Any objects, bounding box based.

HUMAN_BODY_FAST 

Keypoints based, specific to human skeleton, real time performance even on Jetson or low end GPU cards.

HUMAN_BODY_ACCURATE 

Keypoints based, specific to human skeleton, state of the art accuracy, requires powerful GPU.

MULTI_CLASS_BOX_MEDIUM 

Any objects, bounding box based.

HUMAN_BODY_MEDIUM 

Keypoints based, specific to human skeleton, real time performance even on Jetson or low end GPU cards.

PERSON_HEAD_BOX 

Bounding Box detector specialized in person heads, particulary well suited for crowded environement, the person localization is also improved

PERSON_HEAD_BOX_ACCURATE 

Bounding Box detector specialized in person heads, particulary well suited for crowded environement, the person localization is also improved, state of the art accuracy

CUSTOM_BOX_OBJECTS 

For external inference, using your own custom model and/or frameworks. This mode disable the internal inference engine, the 2D bounding box detection must be provided

◆ BODY_PARTS

enum BODY_PARTS
strong

semantic and order of human body keypoints.

Enumerator
NOSE 
NECK 
RIGHT_SHOULDER 
RIGHT_ELBOW 
RIGHT_WRIST 
LEFT_SHOULDER 
LEFT_ELBOW 
LEFT_WRIST 
RIGHT_HIP 
RIGHT_KNEE 
RIGHT_ANKLE 
LEFT_HIP 
LEFT_KNEE 
LEFT_ANKLE 
RIGHT_EYE 
LEFT_EYE 
RIGHT_EAR 
LEFT_EAR 
LAST 

◆ BODY_PARTS_POSE_34

enum BODY_PARTS_POSE_34
strong

ssemantic of human body parts and order keypoints for BODY_FORMAT.POSE_34.

Enumerator
PELVIS 
NAVAL_SPINE 
CHEST_SPINE 
NECK 
LEFT_CLAVICLE 
LEFT_SHOULDER 
LEFT_ELBOW 
LEFT_WRIST 
LEFT_HAND 
LEFT_HANDTIP 
LEFT_THUMB 
RIGHT_CLAVICLE 
RIGHT_SHOULDER 
RIGHT_ELBOW 
RIGHT_WRIST 
RIGHT_HAND 
RIGHT_HANDTIP 
RIGHT_THUMB 
LEFT_HIP 
LEFT_KNEE 
LEFT_ANKLE 
LEFT_FOOT 
RIGHT_HIP 
RIGHT_KNEE 
RIGHT_ANKLE 
RIGHT_FOOT 
HEAD 
NOSE 
LEFT_EYE 
LEFT_EAR 
RIGHT_EYE 
RIGHT_EAR 
LEFT_HEEL 
RIGHT_HEEL 
LAST