Main Content

ACF ベースの一時停止標識検出器の学習

ライブ スクリプトを開く

学習データを使用して、ACF ベースの一時停止標識用オブジェクト検出器に学習させます。

MATLAB パスにイメージを含むフォルダーを追加します。

imageDir = fullfile(matlabroot, 'toolbox', 'vision', 'visiondata', 'stopSignImages');
addpath(imageDir);

グラウンド トゥルース データを読み込みます。これには、一時停止標識と自動車のデータが含まれます。

load('stopSignsAndCarsGroundTruth.mat','stopSignsAndCarsGroundTruth')

ラベル定義を表示して、グラウンド トゥルースに含まれるラベル タイプを確認します。

stopSignsAndCarsGroundTruth.LabelDefinitions
ans=3×3 table
        Name          Type        Group  
    ____________    _________    ________

    {'stopSign'}    Rectangle    {'None'}
    {'carRear' }    Rectangle    {'None'}
    {'carFront'}    Rectangle    {'None'}

学習用の一時停止標識データを選択します。

stopSignGroundTruth = selectLabelsByName(stopSignsAndCarsGroundTruth,'stopSign');

一時停止標識オブジェクト検出器のための学習データを作成します。

trainingData = objectDetectorTrainingData(stopSignGroundTruth);
summary(trainingData)
Variables:

    imageFilename: 41x1 cell array of character vectors

    stopSign: 41x1 cell

ACF ベースのオブジェクト検出器に学習させます。

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 20.3343 seconds.

ACF ベースの検出器をサンプル イメージでテストします。

I = imread('stopSignTest.jpg');
bboxes = detect(acfDetector,I);

検出したオブジェクトを表示します。

annotation = acfDetector.ModelName;
I = insertObjectAnnotation(I,'rectangle',bboxes,annotation);

figure 
imshow(I)

パスからイメージ フォルダーを削除します。

rmpath(imageDir);