You can use the Image Labeler,
Video Labeler, and
Ground Truth Labeler (requires Automated
Driving Toolbox™) apps, along with Computer
Vision Toolbox™ objects and functions, to train algorithms from ground truth data. First, use
your labeling app to interactively label ground truth data in a video, image sequence, image
collection, or custom data source. Then, use the ground truth data to create algorithm
training data. For object detectors, use the
objectDetectorTrainingData function. For semantic segmentation networks, use
Load data for labeling:
Label data and select an automation algorithm: Create ROI and scene labels within the app. For more details, see:
You can choose from one of the built-in algorithms or create your own custom algorithm to label objects in your data. To learn how to create your own automation algorithm, see Create Automation Algorithm for Labeling.
Export labels: After labeling your data, you can
export the labels to the workspace or save them to a file. The labels are exported
groundTruth object. If your data
source consists of multiple image collections, label the entire set of image
collections to obtain an array of
objects. For details about sharing
objects, see Share and Store Labeled Ground Truth Data.
Create training data: To create training data
groundTruth object, use one of these
Sample the ground truth data by specifying a sampling factor. Sampling mitigates
overtraining an object detector on similar samples. For objects created using a
video file or custom data source, the
pixelLabelTrainingData functions write images to disk for
Object detectors — Use one of several Computer Vision Toolbox object detectors. See Object Detection Using Features. For object detectors specific to automated driving, see the Automated Driving Toolbox object detectors listed in Visual Perception (Automated Driving Toolbox).
Semantic segmentation network — Use the
semanticseg function. For more details on training a
semantic segmentation network, see Semantic Segmentation Basics and
the Object Detection Using Deep Learning example.