Обучите основанный на ACF детектор стоп-знака
Используйте обучающие данные для обучения детектора объектов на основе ACF для знаков упора
Добавьте папку, содержащую изображения, в путь MATLAB.
imageDir = fullfile(matlabroot, 'toolbox', 'vision', 'visiondata', 'stopSignImages'); addpath(imageDir);
Загрузка достоверных данных, которая содержит данные для знаков упоров и автомобилей.
load('stopSignsAndCarsGroundTruth.mat','stopSignsAndCarsGroundTruth')
Просмотрите определения меток, чтобы увидеть типы меток в основная истина.
stopSignsAndCarsGroundTruth.LabelDefinitions
ans=3×3 table
Name Type Group
____________ _________ ________
{'stopSign'} Rectangle {'None'}
{'carRear' } Rectangle {'None'}
{'carFront'} Rectangle {'None'}
Выберите данные знака остановки для обучения.
stopSignGroundTruth = selectLabelsByName(stopSignsAndCarsGroundTruth,'stopSign');Создайте обучающие данные для детектора объектов знака упора.
trainingData = objectDetectorTrainingData(stopSignGroundTruth); summary(trainingData)
Variables:
imageFilename: 41x1 cell array of character vectors
stopSign: 41x1 cell
Обучите детектор объектов на основе ACF.
acfDetector = trainACFObjectDetector(trainingData,'NegativeSamplesFactor',2);ACF Object Detector Training The training will take 4 stages. The model size is 34x31. Sample positive examples(~100% Completed) Compute approximation coefficients...Completed. Compute aggregated channel features...Completed. -------------------------------------------- Stage 1: Sample negative examples(~100% Completed) Compute aggregated channel features...Completed. Train classifier with 42 positive examples and 84 negative examples...Completed. The trained classifier has 19 weak learners. -------------------------------------------- Stage 2: Sample negative examples(~100% Completed) Found 84 new negative examples for training. Compute aggregated channel features...Completed. Train classifier with 42 positive examples and 84 negative examples...Completed. The trained classifier has 20 weak learners. -------------------------------------------- Stage 3: Sample negative examples(~100% Completed) Found 84 new negative examples for training. Compute aggregated channel features...Completed. Train classifier with 42 positive examples and 84 negative examples...Completed. The trained classifier has 54 weak learners. -------------------------------------------- Stage 4: Sample negative examples(~100% Completed) Found 84 new negative examples for training. Compute aggregated channel features...Completed. Train classifier with 42 positive examples and 84 negative examples...Completed. The trained classifier has 61 weak learners. -------------------------------------------- ACF object detector training is completed. Elapsed time is 20.7195 seconds.
Протестируйте детектор на основе ACF на образцовом изображении.
I = imread('stopSignTest.jpg');
bboxes = detect(acfDetector,I);
Отображение обнаруженного объекта.
annotation = acfDetector.ModelName;
I = insertObjectAnnotation(I,'rectangle',bboxes,annotation);
figure
imshow(I)
Удалите папку изображений из пути.
rmpath(imageDir);