objectDetectorTrainingData

Create training data for an object detector

Syntax

[imds,blds] = objectDetectorTrainingData(gTruth)

[___,arrds] = objectDetectorTrainingData(gTruth)

trainingDataTable = objectDetectorTrainingData(gTruth)

[___] = objectDetectorTrainingData(gTruth,Name=Value)

Description

[imds,blds] = objectDetectorTrainingData(gTruth) creates an image datastore and a box label datastore training data from the specified ground truth.

You can combine the image and box label datastores using combine(imds,blds) to create a datastore needed for training. Use the combined datastore with the training functions, such as trainACFObjectDetector, trainYOLOv2ObjectDetector, trainFastRCNNObjectDetector, trainFasterRCNNObjectDetector, and trainRCNNObjectDetector.

This function supports parallel computing using multiple MATLAB^® workers. Enable parallel computing using the Computer Vision Toolbox Preferences dialog.

[___,arrds] = objectDetectorTrainingData(gTruth) also returns a datastore arrds, that contains the attributes and sublabels associated with the labels.

trainingDataTable = objectDetectorTrainingData(gTruth) returns a table of training data from the specified ground truth. gTruth is an array of groundTruth objects. You can use the table to train an object detector using the Computer Vision Toolbox™ training functions.

[___] = objectDetectorTrainingData(gTruth,Name=Value) specifies options using one or more name-value arguments in addition to any combination of arguments from previous syntaxes. For example, Verbose=True enables display to the workspace environment.

If you create the groundTruth objects in gTruth using a video file, a custom data source, or an imageDatastore object with different custom read functions, then you can specify any combination of name-value arguments. If you create the groundTruth objects from an image collection or image sequence data source, then you can specify only the SamplingFactor and the LabelData name-value arguments.

Examples

Train a YOLO v2 Vehicle Detector

Train a vehicle detector based on a YOLO v2 network.

Add the folder containing images to the workspace.

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

Load the vehicle ground truth data.

data = load('vehicleTrainingGroundTruth.mat');
gTruth = data.vehicleTrainingGroundTruth;

Load the detector containing the layerGraph object for training.

vehicleDetector = load('yolov2VehicleDetector.mat');
lgraph = vehicleDetector.lgraph

lgraph = 
  LayerGraph with properties:

         Layers: [25×1 nnet.cnn.layer.Layer]
    Connections: [24×2 table]
     InputNames: {'input'}
    OutputNames: {'yolov2OutputLayer'}

Create an image datastore and box label datastore using the ground truth object.

[imds,bxds] = objectDetectorTrainingData(gTruth);

Combine the datastores.

cds = combine(imds,bxds);

Configure training options.

options = trainingOptions('sgdm', ...
       'InitialLearnRate', 0.001, ...
       'Verbose',true, ...
       'MiniBatchSize',16, ...
       'MaxEpochs',30, ...
       'Shuffle','every-epoch', ...
       'VerboseFrequency',10); 

Train the detector.

[detector,info] = trainYOLOv2ObjectDetector(cds,lgraph,options);

*************************************************************************
Training a YOLO v2 Object Detector for the following object classes:

* vehicle

Training on single CPU.
|========================================================================================|
|  Epoch  |  Iteration  |  Time Elapsed  |  Mini-batch  |  Mini-batch  |  Base Learning  |
|         |             |   (hh:mm:ss)   |     RMSE     |     Loss     |      Rate       |
|========================================================================================|
|       1 |           1 |       00:00:00 |         7.50 |         56.2 |          0.0010 |
|       1 |          10 |       00:00:02 |         1.73 |          3.0 |          0.0010 |
|       2 |          20 |       00:00:04 |         1.58 |          2.5 |          0.0010 |
|       2 |          30 |       00:00:06 |         1.36 |          1.9 |          0.0010 |
|       3 |          40 |       00:00:08 |         1.13 |          1.3 |          0.0010 |
|       3 |          50 |       00:00:09 |         1.01 |          1.0 |          0.0010 |
|       4 |          60 |       00:00:11 |         0.95 |          0.9 |          0.0010 |
|       4 |          70 |       00:00:13 |         0.84 |          0.7 |          0.0010 |
|       5 |          80 |       00:00:15 |         0.84 |          0.7 |          0.0010 |
|       5 |          90 |       00:00:17 |         0.70 |          0.5 |          0.0010 |
|       6 |         100 |       00:00:19 |         0.65 |          0.4 |          0.0010 |
|       7 |         110 |       00:00:21 |         0.73 |          0.5 |          0.0010 |
|       7 |         120 |       00:00:23 |         0.60 |          0.4 |          0.0010 |
|       8 |         130 |       00:00:24 |         0.63 |          0.4 |          0.0010 |
|       8 |         140 |       00:00:26 |         0.64 |          0.4 |          0.0010 |
|       9 |         150 |       00:00:28 |         0.57 |          0.3 |          0.0010 |
|       9 |         160 |       00:00:30 |         0.54 |          0.3 |          0.0010 |
|      10 |         170 |       00:00:32 |         0.52 |          0.3 |          0.0010 |
|      10 |         180 |       00:00:33 |         0.45 |          0.2 |          0.0010 |
|      11 |         190 |       00:00:35 |         0.55 |          0.3 |          0.0010 |
|      12 |         200 |       00:00:37 |         0.56 |          0.3 |          0.0010 |
|      12 |         210 |       00:00:39 |         0.55 |          0.3 |          0.0010 |
|      13 |         220 |       00:00:41 |         0.52 |          0.3 |          0.0010 |
|      13 |         230 |       00:00:42 |         0.53 |          0.3 |          0.0010 |
|      14 |         240 |       00:00:44 |         0.58 |          0.3 |          0.0010 |
|      14 |         250 |       00:00:46 |         0.47 |          0.2 |          0.0010 |
|      15 |         260 |       00:00:48 |         0.49 |          0.2 |          0.0010 |
|      15 |         270 |       00:00:50 |         0.44 |          0.2 |          0.0010 |
|      16 |         280 |       00:00:52 |         0.45 |          0.2 |          0.0010 |
|      17 |         290 |       00:00:54 |         0.47 |          0.2 |          0.0010 |
|      17 |         300 |       00:00:55 |         0.43 |          0.2 |          0.0010 |
|      18 |         310 |       00:00:57 |         0.44 |          0.2 |          0.0010 |
|      18 |         320 |       00:00:59 |         0.44 |          0.2 |          0.0010 |
|      19 |         330 |       00:01:01 |         0.38 |          0.1 |          0.0010 |
|      19 |         340 |       00:01:03 |         0.41 |          0.2 |          0.0010 |
|      20 |         350 |       00:01:04 |         0.39 |          0.2 |          0.0010 |
|      20 |         360 |       00:01:06 |         0.42 |          0.2 |          0.0010 |
|      21 |         370 |       00:01:08 |         0.42 |          0.2 |          0.0010 |
|      22 |         380 |       00:01:10 |         0.39 |          0.2 |          0.0010 |
|      22 |         390 |       00:01:12 |         0.37 |          0.1 |          0.0010 |
|      23 |         400 |       00:01:13 |         0.37 |          0.1 |          0.0010 |
|      23 |         410 |       00:01:15 |         0.35 |          0.1 |          0.0010 |
|      24 |         420 |       00:01:17 |         0.29 |      8.3e-02 |          0.0010 |
|      24 |         430 |       00:01:19 |         0.36 |          0.1 |          0.0010 |
|      25 |         440 |       00:01:21 |         0.28 |      7.9e-02 |          0.0010 |
|      25 |         450 |       00:01:22 |         0.29 |      8.1e-02 |          0.0010 |
|      26 |         460 |       00:01:24 |         0.28 |      8.0e-02 |          0.0010 |
|      27 |         470 |       00:01:26 |         0.27 |      7.1e-02 |          0.0010 |
|      27 |         480 |       00:01:28 |         0.25 |      6.3e-02 |          0.0010 |
|      28 |         490 |       00:01:30 |         0.24 |      5.9e-02 |          0.0010 |
|      28 |         500 |       00:01:31 |         0.29 |      8.4e-02 |          0.0010 |
|      29 |         510 |       00:01:33 |         0.35 |          0.1 |          0.0010 |
|      29 |         520 |       00:01:35 |         0.31 |      9.3e-02 |          0.0010 |
|      30 |         530 |       00:01:37 |         0.18 |      3.1e-02 |          0.0010 |
|      30 |         540 |       00:01:38 |         0.22 |      4.6e-02 |          0.0010 |
|========================================================================================|
Detector training complete.
*************************************************************************

Read a test image.

I = imread('detectcars.png');

Run the detector.

[bboxes,scores] = detect(detector,I);

Display the results.

if(~isempty(bboxes))
  I = insertObjectAnnotation(I,'rectangle',bboxes,scores);
end
figure
imshow(I)

Train ACF-Based Stop Sign Detector

Use training data to train an ACF-based object detector for stop signs

Add the folder containing images to the MATLAB path.

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

Load ground truth data, which contains data for stops signs and cars.

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

View the label definitions to see the label types in the ground truth.

stopSignsAndCarsGroundTruth.LabelDefinitions

ans=3×3 table
        Name          Type        Group  
    ____________    _________    ________

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

Select the stop sign data for training.

stopSignGroundTruth = selectLabelsByName(stopSignsAndCarsGroundTruth,'stopSign');

Create the training data for a stop sign object detector.

trainingData = objectDetectorTrainingData(stopSignGroundTruth);
summary(trainingData)

Variables:

    imageFilename: 41x1 cell array of character vectors

    stopSign: 41x1 cell

Train an ACF-based object detector.

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 26.224 seconds.

Test the ACF-based detector on a sample image.

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

Display the detected object.

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

figure 
imshow(I)

Remove the image folder from the path.

rmpath(imageDir); 

Read all label attributes from groundTruth

Load image locations, label definitions and label data.

data = load('labelsWithAttributes.mat');
images = fullfile(matlabroot,'toolbox','vision','visiondata','stopSignImages', data.imageFilenames);

Create a ground truth object.

dataSource = groundTruthDataSource(images);
gTruth = groundTruth(groundTruthDataSource(images), data.labeldefs, data.labelData);

Create an image datastore, box label datastore, and array datastore using the ground truth object.

[imds, blds, arrds] = objectDetectorTrainingData(gTruth);

Read all attributes.

readall(arrds)

ans=2×1 cell array
    {1x1 struct}
    {1x1 struct}

Input Arguments

gTruth — Ground truth data

scalar | array of groundTruth objects

Ground truth data, specified as a scalar or an array of groundTruth objects. You can create ground truth objects from existing ground truth data by using the groundTruth object.

If you use custom data sources in groundTruth with parallel computing enabled, then the reader function is expected to work with a pool of MATLAB workers to read images from the data source in parallel.

Name-Value Arguments

Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

Before R2021a, use commas to separate each name and value, and enclose Name in quotes.

Example: (SamplingFactor=5) sets the subsampling factor to 5.

SamplingFactor — Factor for subsampling images

auto (default) | integer | vector of integers

Factor for subsampling images in the ground truth data source, specified as auto, an integer, or a vector of integers. For a sampling factor of N, the returned training data includes every Nth image in the ground truth data source. The function ignores ground truth images with empty label data. To set the SamplingFactor with projected cuboid data, you must specify the LabelData name-value argument to labelType.ProjectedCuboid.

Use sampled data to reduce repeated data, such as a sequence of images with the same scene and labels. It can also help in reducing training time.

Value	Sampling Factor
"auto"	The function samples data sources with timestamps, such as a video, with a factor of 5, and 1 for a collection of images.
Integer	Manually set the sampling factor to apply to all data.
Vector of integers	When you input an array of ground truth objects, the function uses the sampling factor specified by the corresponding vector element.

LabelData — Type of label to extract from ground truth data

"labelType.Rectangle" (default) | "labelType.ProjectedCuboid" | character vector

Type of label to extract from ground truth data, specified as "labelType.Rectangle" or "labelType.ProjectedCuboid". Use the type of label consistent with the type of object detector you want to train.

WriteLocation — Name of folder

pwd (current working folder) (default) | string scalar | character vector

Folder name to write extracted images to, specified as a string scalar or character vector. The specified folder must exist and have write permissions.

This argument applies only for:

• groundTruth objects created using a video file or a custom data source.

• An array of groundTruth objects created using imageDatastore , with different custom read functions.

The function ignores this argument when:

• The input groundTruth object was created from an image sequence data source.

• The array of input groundTruth objects all contain image datastores using the same custom read function.

• Any of the input groundTruth objects containing datastores, use the default read functions.

ImageFormat — Image file format

PNG (default) | string scalar | character vector

Image file format, specified as a string scalar or character vector. File formats must be supported by imwrite.

This argument applies only for:

• groundTruth objects created using a video file or a custom data source.

• An array of groundTruth objects created using imageDatastore with different custom read functions.

The function ignores this argument when:

• The input groundTruth object was created from an image sequence data source.

• The array of input groundTruth objects all contain image datastores using the same custom read function.

• Any of the input groundTruth objects containing datastores, use the default read functions.

NamePrefix — Prefix for output image file names

string scalar | character vector

Prefix for output image file names, specified as a string scalar or character vector. The image files are named as:

<name_prefix><source_number>_<image_number>.<image_format>

The default value uses the name of the data source that the images were extracted from, strcat(sourceName,"_"), for video and a custom data source, or "datastore", for an image datastore.

This argument applies only for:

• groundTruth objects created using a video file or a custom data source.

• An array of groundTruth objects created using imageDatastore with different custom read functions.

The function ignores this argument when:

• The input groundTruth object was created from an image sequence data source.

• The array of input groundTruth objects all contain image datastores using the same custom read function.

• Any of the input groundTruth objects containing datastores, use the default read functions.

Verbose — Flag to display training progress

true (1) (default) | false (0)

Flag to display training progress at the MATLAB command line, specified as either true (1) or false (0). This property applies only for groundTruth objects created using a video file or a custom data source.

Output Arguments

imds — Image datastore

imageDatastore object

Image datastore, returned as an imageDatastore object containing images extracted from the gTruth objects. The images in imds contain at least one class of annotated labels. The function ignores images that are not annotated.

blds — Box label datastore

boxLabelDatastore object

Box label datastore, returned as a boxLabelDatastore object. The datastore contains categorical vectors for ROI label names and M-by-4 matrices of M bounding boxes. The locations and sizes of the bounding boxes are represented as double M-by-4 element vectors in the format [x,y,width,height].

arrds — Array datastore

struct array

Array datastore, returned as a struct array. The fields of the struct contain the attributes and sublabel names for the corresponding labels in the box label datastore blds. The sublabel data is packaged into the struct with a Position field along with the fields that correspond to the sublabel attributes.

trainingDataTable — Training data table

table

Training data table, returned as a table with two or more columns. The first column of the table contains image file names with paths. The images can be grayscale or truecolor (RGB) and in any format supported by imread. Each of the remaining columns correspond to an ROI label and contains the locations of bounding boxes in the image (specified in the first column), for that label. The bounding boxes are specified as M-by-4 matrices of M bounding boxes in the format [x,y,width,height]. [x,y] specifies the upper-left corner location. To create a ground truth table, you can use the Image Labeler app or Video Labeler app.

The output table ignores any sublabel or attribute data present in the input gTruth object.

Version History

Introduced in R2017a

R2022b: Project cuboids from 3-D world coordinates to 2-D image coordinates

• Updated to support 3-D projected cuboid labels.

• Returns extracted attributes and sublabels as a third output. The attributes and sublabels are packaged as an array datastore.