Package org.photonvision.jni

Class RknnDetectorJNI.RknnObjectDetector

java.lang.Object

org.photonvision.jni.RknnDetectorJNI.RknnObjectDetector

Enclosing class:

RknnDetectorJNI

public static class RknnDetectorJNI.RknnObjectDetector
extends Object

Constructor Summary

Constructors

Constructor	Description
RknnObjectDetector(String modelPath, List<String> labels, org.photonvision.rknn.RknnJNI.ModelVersion version)

Method Summary

Modifier and Type	Method	Description
List<NeuralNetworkPipeResult>	detect(org.opencv.core.Mat in, double nmsThresh, double boxThresh)	Detect forwards using this model
List<String>	getClasses()
void	release()

Methods inherited from class java.lang.Object

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

Constructor Details

RknnObjectDetector

public RknnObjectDetector(String modelPath,
 List<String> labels,
 org.photonvision.rknn.RknnJNI.ModelVersion version)

Method Details

getClasses

public List<String> getClasses()

detect

public List<NeuralNetworkPipeResult> detect(org.opencv.core.Mat in,
 double nmsThresh,
 double boxThresh)

Detect forwards using this model

Parameters:

in - The image to process

nmsThresh - Non-maximum supression threshold. Probably should not change

boxThresh - Minimum confidence for a box to be added. Basically just confidence threshold

release

public void release()