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

Enumerations

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_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

◆ 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

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.