org.firstinspires.ftc.robotcore.external.tfod

Class TfodBase

java.lang.Object

org.firstinspires.ftc.robotcore.external.tfod.TfodBase

Direct Known Subclasses:

TfodCustomModel, TfodRoverRuckus, TfodSkyStone

public abstract class TfodBase
extends java.lang.Object

An abstract base class that provides simplified access to TensorFlow Object Detection.

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	TfodBase()
protected	TfodBase(java.lang.String assetName, java.lang.String[] labels)

Method Summary

Modifier and Type	Method and Description
void	activate() Activates object detection.
void	close() Deactivates object detection and cleans up.
void	deactivate() Deactivates object detection.
java.util.List<Recognition>	getRecognitions() Returns the list of recognitions.
java.util.List<Recognition>	getUpdatedRecognitions() Returns the list of recognitions, but only if they are different than the last call to getUpdatedRecognitions().
void	initialize(VuforiaBase vuforiaBase, float minimumConfidence, boolean useObjectTracker, boolean enableCameraMonitoring) Initializes TensorFlow Object Detection.
void	setClippingMargins(int left, int top, int right, int bottom) Sets the number of pixels to obscure on the left, top, right, and bottom edges of each image passed to the TensorFlow object detector.
void	setModelFromAsset(java.lang.String assetName, java.lang.String[] labels)
void	setModelFromFile(java.lang.String tfliteModelFilename, java.lang.String[] labels)
void	setZoom(double magnification, double aspectRatio) Indicates that only the zoomed center area of each image will be passed to the TensorFlow object detector.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

TfodBase

protected TfodBase(java.lang.String assetName,
                   java.lang.String[] labels)

TfodBase

protected TfodBase()

Method Detail

setModelFromAsset

public void setModelFromAsset(java.lang.String assetName,
                              java.lang.String[] labels)

setModelFromFile

public void setModelFromFile(java.lang.String tfliteModelFilename,
                             java.lang.String[] labels)

initialize

public void initialize(VuforiaBase vuforiaBase,
                       float minimumConfidence,
                       boolean useObjectTracker,
                       boolean enableCameraMonitoring)

Initializes TensorFlow Object Detection.

activate

public void activate()

Activates object detection.

Throws:

java.lang.IllegalStateException - if initialized has not been called yet.

deactivate

public void deactivate()

Deactivates object detection.

Throws:

java.lang.IllegalStateException - if initialized has not been called yet.

setClippingMargins

public void setClippingMargins(int left,
                               int top,
                               int right,
                               int bottom)

Sets the number of pixels to obscure on the left, top, right, and bottom edges of each image passed to the TensorFlow object detector. The size of the images are not changed, but the pixels in the margins are colored black.

setZoom

public void setZoom(double magnification,
                    double aspectRatio)

Indicates that only the zoomed center area of each image will be passed to the TensorFlow object detector. For no zooming, set magnification to 1.0. For best results, the aspect ratio should match the aspect ratio of the images that were used to train the TensorFlow model (1.7777 for 16/9).

getUpdatedRecognitions

public java.util.List<Recognition> getUpdatedRecognitions()

Returns the list of recognitions, but only if they are different than the last call to getUpdatedRecognitions().

getRecognitions

public java.util.List<Recognition> getRecognitions()

Returns the list of recognitions.

close

public void close()

Deactivates object detection and cleans up.