Ground Detection(segmentation) for Autonomous Driving

close all;

% clear all;

clc;

resnet50();

outputFolder = fullfile('/home/hyphen/Downloads','data_road_224');

imgDir = fullfile(outputFolder,'training','image_2');

imds = imageDatastore(imgDir);

%auimds = augmentedImageDatastore([375 1242 3],imds);

I = readimage(imds,1);

I = histeq(I);

imshow(I)

classNames = [

"rightroad"

"leftroad"

"environment"

];

labelIDs = kittiPixelLabelIDs();

labelDir = fullfile(outputFolder,'training','gt_image_2');

% imds1 = imageDatastore(labelDir);

% pxds1 = augmentedImageDatastore([375 1242 3],imds1);

%

% filename = '/tmp/data_road/training/gt1';

% pxds2 = imwrite(pxds1,filename);

pxds = pixelLabelDatastore(labelDir,classNames,labelIDs);

C = readimage(pxds,1);

cmap = kittiColorMap;

B = labeloverlay(I,C,'ColorMap',cmap);

imshow(B)

pixelLabelColorbar(cmap,classNames);

tbl = countEachLabel(pxds)

% Prepare Training, Validation, and Test Sets

[imdsTrain, imdsVal, imdsTest, pxdsTrain, pxdsVal, pxdsTest] = partitionkittiData(imds,pxds);

numTrainingImages = numel(imdsTrain.Files)

numValImages = numel(imdsVal.Files)

numTestingImages = numel(imdsTest.Files)

% Create the Network

imageSize = [224 224 3];

numClasses = numel(classNames)

lgraph = deeplabv3plusLayers(imageSize, numClasses, "resnet50");

% Balance Classes Using Class Weighting

imageFreq = tbl.PixelCount ./ tbl.ImagePixelCount;

classWeights = median(imageFreq) ./ imageFreq

pxLayer = pixelClassificationLayer('Name','labels','Classes',tbl.Name,'ClassWeights',classWeights);

lgraph = replaceLayer(lgraph,"classification",pxLayer);

% Select Training Options

% Define validation data.

pximdsVal = pixelLabelImageDatastore(imdsVal,pxdsVal);

% Define training options.

options = trainingOptions('sgdm', 'LearnRateSchedule','piecewise', 'LearnRateDropPeriod',10,'LearnRateDropFactor',0.3,'Momentum',0.9,'InitialLearnRate',0.001,'L2Regularization',0.005,'ValidationData',pximdsVal,'MaxEpochs',50, 'MiniBatchSize',1,'Shuffle','every-epoch','CheckpointPath', tempdir,'VerboseFrequency',2,'Plots','training-progress','ValidationPatience', Inf);

% Data Augmentation

augmenter = imageDataAugmenter('RandXReflection',true,'RandXTranslation',[-10 10],'RandYTranslation',[-10 10]);

% Start Training

pximds = pixelLabelImageDatastore(imdsTrain,pxdsTrain,'DataAugmentation',augmenter);

doTraining = true;

if doTraining

[net, info] = trainNetwork(pximds,lgraph,options);

else

data = load(pretrainedNetwork);

net = data.net;

end

% Test Network on One Image

I1 = readimage(imdsTest,30);

J = histeq(I1);

figure

imshow(I1)

C = semanticseg(J, net);

B = labeloverlay(J,C,'Colormap',cmap,'Transparency',0.3);

figure

imshow(B)

pixelLabelColorbar(cmap, classNames);

function labelIDs = kittiPixelLabelIDs()

% Return the label IDs corresponding to each class.

%

% The CamVid dataset has 32 classes. Group them into 11 classes following

% the original SegNet training methodology [1].

%

% The 11 classes are:

% "Sky" "Building", "Pole", "Road", "Pavement", "Tree", "SignSymbol",

% "Fence", "Car", "Pedestrian", and "Bicyclist".

%

% CamVid pixel label IDs are provided as RGB color values. Group them into

% 11 classes and return them as a cell array of M-by-3 matrices. The

% original CamVid class names are listed alongside each RGB value. Note

% that the Other/Void class are excluded below.

labelIDs = { ...

% "rightroad"

[

255 000 255; ... % "rightroad"

]

% "leftroad"

[

000 000 000; ... % "leftroad"

]

% "environment"

[

255 000 000; ... % "environment"

]

};

end

function cmap = kittiColorMap()

% Define the colormap used by CamVid dataset.

cmap = [

255 0 255 % rightroad

0 0 0 % leftroad

255 0 0 % environment

];

% Normalize between [0 1].

cmap = cmap ./ 255;

end

function pixelLabelColorbar(cmap, classNames)

% Add a colorbar to the current axis. The colorbar is formatted

% to display the class names with the color.

colormap(gca,cmap)

% Add colorbar to current figure.

c = colorbar('peer', gca);

% Use class names for tick marks.

c.TickLabels = classNames;

numClasses = size(cmap,1);

% Center tick labels.

c.Ticks = 1/(numClasses*2):1/numClasses:1;

% Remove tick mark.

c.TickLength = 0;

end

function [imdsTrain, imdsVal, imdsTest, pxdsTrain, pxdsVal, pxdsTest] = partitionkittiData(imds,pxds)

% Partition CamVid data by randomly selecting 60% of the data for training. The

% rest is used for testing.

% Set initial random state for example reproducibility.

rng(0);

numFiles = numel(imds.Files);

shuffledIndices = randperm(numFiles);

% Use 60% of the images for training.

numTrain = round(0.60 * numFiles);

trainingIdx = shuffledIndices(1:numTrain);

% Use 20% of the images for validation

numVal = round(0.20 * numFiles);

valIdx = shuffledIndices(numTrain+1:numTrain+numVal);

% Use the rest for testing.

testIdx = shuffledIndices(numTrain+numVal+1:end);

% Create image datastores for training and test.

trainingImages = imds.Files(trainingIdx);

valImages = imds.Files(valIdx);

testImages = imds.Files(testIdx);

imdsTrain = imageDatastore(trainingImages);

imdsVal = imageDatastore(valImages);

imdsTest = imageDatastore(testImages);

% Extract class and label IDs info.

classes = pxds.ClassNames;

labelIDs = kittiPixelLabelIDs();

% Create pixel label datastores for training and test.

trainingLabels = pxds.Files(trainingIdx);

valLabels = pxds.Files(valIdx);

testLabels = pxds.Files(testIdx);

pxdsTrain = pixelLabelDatastore(trainingLabels, classes, labelIDs);

pxdsVal = pixelLabelDatastore(valLabels, classes, labelIDs);

pxdsTest = pixelLabelDatastore(testLabels, classes, labelIDs);

end