org.opencv.dnn

Class SegmentationModel

java.lang.Object

org.opencv.dnn.Net

org.opencv.dnn.Model

org.opencv.dnn.SegmentationModel

public class SegmentationModel
extends Model

This class represents high-level API for segmentation models SegmentationModel allows to set params for preprocessing input image. SegmentationModel creates net from file with trained weights and config, sets preprocessing input, runs forward pass and returns the class prediction for each pixel.

Field Summary

Fields inherited from class org.opencv.dnn.Net

nativeObj

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	SegmentationModel(long addr)
	SegmentationModel(Net network) Create model from deep learning network.
	SegmentationModel(String model) Create segmentation model from network represented in one of the supported formats.
	SegmentationModel(String model, String config) Create segmentation model from network represented in one of the supported formats.

Method Summary

Modifier and Type	Method and Description
static SegmentationModel	__fromPtr__(long addr)
protected void	finalize()
void	segment(Mat frame, Mat mask) Given the input frame, create input blob, run net

Methods inherited from class org.opencv.dnn.Model

predict, setInputCrop, setInputMean, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputParams, setInputScale, setInputSize, setInputSize, setInputSwapRB

Methods inherited from class org.opencv.dnn.Net

connect, dump, dumpToFile, empty, enableFusion, forward, forward, forward, forward, forward, getFLOPS, getFLOPS, getFLOPS, getFLOPS, getLayer, getLayerId, getLayerNames, getLayersCount, getLayerTypes, getMemoryConsumption, getMemoryConsumption, getMemoryConsumption, getNativeObjAddr, getParam, getParam, getPerfProfile, getUnconnectedOutLayers, getUnconnectedOutLayersNames, readFromModelOptimizer, readFromModelOptimizer, setHalideScheduler, setInput, setInput, setInput, setInput, setInputShape, setInputsNames, setParam, setPreferableBackend, setPreferableTarget

Methods inherited from class java.lang.Object

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

Constructor Detail

SegmentationModel

protected SegmentationModel(long addr)

SegmentationModel

public SegmentationModel(Net network)

Create model from deep learning network.

Parameters:

network - Net object.

SegmentationModel

public SegmentationModel(String model,
                         String config)

Create segmentation model from network represented in one of the supported formats. An order of model and config arguments does not matter.

Parameters:

model - Binary file contains trained weights.

config - Text file contains network configuration.

SegmentationModel

public SegmentationModel(String model)

Create segmentation model from network represented in one of the supported formats. An order of model and config arguments does not matter.

Parameters:

model - Binary file contains trained weights.

Method Detail

__fromPtr__

public static SegmentationModel __fromPtr__(long addr)

segment

public void segment(Mat frame,
                    Mat mask)

Given the input frame, create input blob, run net

Parameters:

mask - Allocated class prediction for each pixel

frame - automatically generated

finalize

protected void finalize()
                 throws Throwable

Overrides:

finalize in class Model

Throws:

Throwable