Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

Detection

public abstract class Detection

Represents one detected object in the results of ERROR(/com.google.mediapipe.tasks.version.objectdetector.ObjectDetector).

Public Constructors

Detection()

Public Methods

abstract RectF	boundingBox() A `ERROR(/RectF)` object to represent the bounding box of the detected object.
abstract List<Category>	categories() A list of `Category` objects.
static Detection	create(List<Category> categories, RectF boundingBox, Optional<List<NormalizedKeypoint>> keypoints) Creates a `Detection` instance from a list of `Category` and a bounding box.
static Detection	create(List<Category> categories, RectF boundingBox) Creates a `Detection` instance from a list of `Category` and a bounding box.
static Detection	createFromProto(com.google.mediapipe.formats.proto.DetectionProto.Detection detectionProto) Creates a `Detection` instance from a `ERROR(/com.google.mediapipe.formats.proto.DetectionProto.Detection)` protobuf message.
abstract Optional<List<NormalizedKeypoint>>	keypoints() An optional list of `NormalizedKeypoint` associated with the detection.

Inherited Methods

From class java.lang.Object

boolean	equals(Object arg0)
final Class<?>	getClass()
int	hashCode()
final void	notify()
final void	notifyAll()
String	toString()
final void	wait(long arg0, int arg1)
final void	wait(long arg0)
final void	wait()

Public Constructors

public Detection ()

Public Methods

public abstract RectF boundingBox ()

A ERROR(/RectF) object to represent the bounding box of the detected object.

public abstract List<Category> categories ()

A list of Category objects.

public static Detection create (List<Category> categories, RectF boundingBox, Optional<List<NormalizedKeypoint>> keypoints)

Creates a Detection instance from a list of Category and a bounding box.

Parameters

categories	a list of `Category` objects that contain category name, display name, score, and the label index.
boundingBox	a `ERROR(/RectF)` object to represent the bounding box.
keypoints	an optional list of `ERROR(/NormalizedKeypoints)` associated with the detection.

public static Detection create (List<Category> categories, RectF boundingBox)

Creates a Detection instance from a list of Category and a bounding box.

Parameters

categories	a list of `Category` objects that contain category name, display name, score, and the label index.
boundingBox	a `ERROR(/RectF)` object to represent the bounding box.

public static Detection createFromProto (com.google.mediapipe.formats.proto.DetectionProto.Detection detectionProto)

Creates a Detection instance from a ERROR(/com.google.mediapipe.formats.proto.DetectionProto.Detection) protobuf message.

Parameters

detectionProto	a `ERROR(/com.google.mediapipe.formats.proto.DetectionProto.Detection)` protobuf message.

public abstract Optional<List<NormalizedKeypoint>> keypoints ()

An optional list of NormalizedKeypoint associated with the detection. Keypoints represent interesting points related to the detection. For example, the keypoints represent the eyes, ear and mouth from face detection model. Or in the template matching detection, e.g. KNIFT, they can represent the feature points for template matching.