Ground Truth Labeler

Label ground truth data for automated driving applications

Description

The Ground Truth Labeler app enables you to label ground truth data in a video, in an image sequence, or from a custom data source reader. Using the app, you can:

• Define rectangular regions of interest (ROI) labels, polyline ROI labels, pixel ROI labels, and scene labels. Use these labels to interactively label your ground truth data.

• Use built-in detection or tracking algorithms to label your ground truth data.

• Write, import, and use your own custom automation algorithm to automatically label ground truth.

• Evaluate the performance of your label automation algorithms using a visual summary.

• Export the labeled ground truth as a groundTruth object. You can use this object for system verification or for training an object detector or semantic segmentation network.

• Display time-synchronized signals, such as lidar or CAN bus data, using the driving.connector.Connector API.

To learn more about this app, see Get Started with the Ground Truth Labeler.

Open the Ground Truth Labeler App

• MATLAB^® Toolstrip: On the Apps tab, under Automotive, click the app icon.

• MATLAB command prompt: Enter groundTruthLabeler.

Examples

Related Examples

• Get Started with the Ground Truth Labeler
• Automate Ground Truth Labeling of Lane Boundaries
• Automate Ground Truth Labeling for Semantic Segmentation
• Automate Attributes of Labeled Objects
• Evaluate Lane Boundary Detections Against Ground Truth Data
• Evaluate and Visualize Lane Boundary Detections Against Ground Truth

Programmatic Use

groundTruthLabeler

groundTruthLabeler opens a new session of the app, enabling you to label ground truth data.

groundTruthLabeler(videoFileName)

groundTruthLabeler(videoFileName) opens the app and loads the input video. The video file must have an extension supported by VideoReader.

Example: groundTruthLabeler('caltech_cordova1.avi')

groundTruthLabeler(imageSeqFolder)

groundTruthLabeler(imageSeqFolder) opens the app and loads the image sequence from the input folder. An image sequence is an ordered set of images that resemble a video. The images must be the same size. imageSeqFolder must be a string scalar or character vector that specifies the folder containing the image files. The image files must have extensions supported by imformats and are loaded in the order returned by the dir function.

To label a collection of unordered images that can vary in size, use the Image Labeler app instead.

groundTruthLabeler(imageSeqFolder,timestamps)

groundTruthLabeler(imageSeqFolder,timestamps) opens the app and loads a sequence of images with their corresponding timestamps. timestamps must be a duration vector of the same length as the number of images in the sequence.

For example, load a sequence of road images and their corresponding timestamps into the app.

imageDir = fullfile(toolboxdir('driving'),'drivingdata','roadSequence');
load(fullfile(imageDir,'timeStamps.mat'))
groundTruthLabeler(imageDir,timeStamps)

groundTruthLabeler(gtSource)

groundTruthLabeler(gtSource) opens the app and loads the groundTruthDataSource object, gtSource. The object contains a custom data source and corresponding timestamps.

groundTruthLabeler(sessionFile)

groundTruthLabeler(sessionFile) opens the app and loads a saved app session, sessionFile. The sessionFile input contains the path and file name. The MAT-file that sessionFile points to contains the saved session.

groundTruthLabeler(___,'ConnectorTargetHandle','connector')

groundTruthLabeler(___,'ConnectorTargetHandle','connector') opens the app with a custom connector. 'connector' is a handle to a driving.connector.Connector class. The handle implements a custom analysis or visualization tool that is time-synchronized with the Ground Truth Labeler app. For example, to associate a connector target defined in class MyConnectorClass, specify @MyConnectorClass.

For example, open the app, load a 10-second video into it, and open a lidar visualization tool that is time-synchronized to the video.

groundTruthLabeler('01_city_c2s_fcw_10s.mp4','ConnectorTargetHandle',@LidarDisplay);

Limitations

• The built-in automation algorithms support the automation of rectangular ROI labels only. When you select a built-in algorithm and click Automate, scene labels, pixel labels, polyline labels, sublabels, and attributes are not imported into the automation session. To automate the labeling of these features, create a custom automation algorithm.

• Pixel ROI labels do not support sublabels or attributes.

• The Label Summary window does not support sublabels or attributes

Tips

• To avoid having to relabel ground truth with new labels, organize the labeling scheme you want to use before marking your ground truth.

Algorithms

You can use label automation algorithms to speed up labeling within the app. To create your own label automation algorithm to use within the app, see Create Automation Algorithm for Labeling (Computer Vision Toolbox). You can also use one of the provided built-in algorithms. Follow these steps:

1. Load the data you want to label, and create at least one label definition.

2. On the app toolstrip, click Select Algorithm, and select one of the built-in automation algorithms.

3. Click Automate, and then follow the automation instructions in the right pane of the automation window.

ACF Vehicle Detector

Detect and label vehicles using aggregate channel features (ACF). This algorithm is based on the vehicleDetectorACF function. To use this algorithm, you must define at least one rectangle ROI label. You do not need to draw any ROI labels.

To help improve the algorithm results, first click Settings. You can change any of these settings.

• The pretrained vehicle detector model that the algorithm uses — The 'full-view' model was trained using unoccluded images of the front, rear, left, and right sides of vehicles. The 'front-rear-view' model was trained using images of only the front and rear sides of the vehicle.

• The overlap ratio threshold, from 0 to 1, for detecting vehicles — When rectangle ROIs overlap by more than this threshold, the algorithm discards one of the ROIs.

• The classification score threshold for detecting vehicles — Increase the score to increase the prediction confidence of the algorithm. Rectangles with scores below this threshold are discarded.

You can also configure the detector with a calibrated monocular camera by importing a monoCamera object into the MATLAB workspace. Specify the length and width ranges of the vehicle in world units, such as meters.

ACF People Detector

Detect and label people using aggregate channel features (ACF). This algorithm is based on the peopleDetectorACF function. To use this algorithm, you must define at least one rectangle ROI label. You do not need to draw any ROI labels.

To help improve the algorithm results, first click Settings. You can change any of these settings.

• The pretrained people detector model that the algorithm uses — The 'inria-100x41' model was trained using the INRIA person data set. The 'caltech-50x21' model was trained using the Caltech Pedestrian data set.

• The overlap ratio threshold, from 0 to 1, for detecting people — When rectangle ROIs overlap by more than this threshold, the algorithm discards one of the ROIs.

• The classification score threshold for detecting people — Increase the score to increase the prediction confidence of the algorithm. Rectangles with scores below this threshold are discarded.

Point Tracker

Track and label one or more rectangle ROI labels over short intervals by using the Kanade-Lucas-Tomasi (KLT) algorithm. This algorithm is based on the vision.PointTracker System object™. To use this algorithm, you must define at least one rectangle ROI label, but you do not need to draw any ROI labels.

To change the feature detector used to obtain the initial points for tracking, click Settings. This table shows the feature detector options.

Feature Detector	Description	Equivalent Function
Minimum Eigen Value	Detect corners by using the minimum eigenvalue algorithm.	detectMinEigenFeatures
Harris	Detect corners by using the Harris–Stephens algorithm.	detectHarrisFeatures
FAST	Detect corners by using the features from accelerated segment test (FAST) algorithm.	detectFASTFeatures
BRISK	Detect features by using the binary robust invariant scalable keypoints (BRISK) algorithm.	detectBRISKFeatures
KAZE	Detect features by using nonlinear diffusion to construct a scale space of an image, and then detecting multiscale corner features (KAZE features) from that scale space.	detectKAZEFeatures
SURF	Detect blob features by using the speeded-up robust features (SURF) algorithm.	detectSURFFeatures
MSER	Detect regions by using the maximally stable extremal regions (MSER) algorithm.	detectMSERFeatures

Temporal Interpolator

Estimate rectangle ROIs between frames by interpolating the ROI locations across the time interval. To use this algorithm, you must draw a rectangle ROI on a minimum of two frames: one at the beginning of the interval and one at the end of the interval. The interpolation algorithm estimates and draws ROIs in the intermediate frames.

Consider a video with 10 frames. The first frame has a rectangle ROI centered at [5, 5]. The 10th frame has a rectangle ROI centered at [25, 25]. At each frame, the algorithm moves the ROI 2 pixels in the x-direction and 2 pixels in the y-direction. Therefore, the algorithm centers the ROI at [7, 7] in the second frame, [9, 9] in the third frame, and so on, up to [23, 23] in the second-to-last frame.

Lane Boundary Detector

Detect and label lane boundaries using an estimated bird’s-eye-view projected image. To use this algorithm, you must define at least one line ROI label. You do not need to draw any ROI labels. To detect lane boundaries, the algorithm follows these steps:

1. It makes an initial guess at the placement of the lane boundaries in the image.

2. It transforms the ROI around the lanes into a bird's-eye view image to make the lanes parallel and remove distortion.

3. It uses this image to segment the lane boundaries.

To help improve the algorithm results, first click Settings. You can change any of these settings.

• The placement of the lane lines for generating the bird's-eye view image

• The ROI around the lanes, which you can expand to include more than just the ego lane boundaries in the image

• The pixel width of detected lane boundaries in the image

You can also change the number of lane boundaries that you want to detect. The default number of lane boundaries is 2.