Labeling

Interactive point cloud labeling for object detection, semantic segmentation, and classification

Use the Lidar Labeler app to interactively label ground truth data in a point cloud or a point cloud sequence. You can label cuboids and polylines for object detection, voxels for semantic segmentation, and scenes for point cloud classification.

The app provides algorithms to automate the labeling process for object tacking and interpolation. You can use one of the included algorithms or create and import a custom automation algorithm. For more information, see Create Automation Algorithm for Labeling.

For information on how to start labeling a point cloud sequence, see Get Started with the Lidar Labeler.

You can also use Lidar Toolbox™ functions to define labels and programmatically automate the labeling process.

Apps

Lidar Labeler

Label ground truth data in lidar point clouds (Since R2020b)

Functions

expand all

Create Labels and Label Definitions

Use Lidar Labels

`groundTruthLidar`	Lidar ground truth label data (Since R2020b)
`selectLabels`	Select ground truth data by label name or type (Since R2020b)
`selectLabelsByGroup`	Select ground truth data by label group name (Since R2020b)
`selectLabelsByName`	Select ground truth data by label name (Since R2020b)
`selectLabelsByType`	Select ground truth data by label type (Since R2020b)
`changeFilePaths`	Change file paths in ground truth data (Since R2020b)
`labelType`	Label type enumerations for labeling
`lidarLabelType`	Lidar label type enumerations for labeling (Since R2022a)
`attributeType`	Attribute type enumerations for labeling

Create Label Definitions

`labelDefinitionCreatorLidar`	Store, modify, and create label definitions tables for lidar (Since R2020b)
`addAttribute`	Add attribute to label in label definition creator for lidar workflow (Since R2020b)
`addLabel`	Add label to label definition creator object for lidar workflow (Since R2020b)
`create`	Create label definitions table from label definition creator object for lidar workflow (Since R2020b)
`editAttributeDescription`	Modify attribute description in label definition creator object for lidar workflow (Since R2020b)
`editGroupName`	Change group name in label definition creator for lidar workflow (Since R2020b)
`editLabelDescription`	Modify label description in label definition creator for lidar workflow (Since R2020b)
`editLabelGroup`	Modify label group name in label definition creator object for lidar workflow (Since R2020b)
`info`	Display label or attribute information stored in label definition creator for lidar workflow (Since R2020b)
`removeAttribute`	Remove attribute from label in label definition creator for lidar workflow (Since R2020b)
`removeLabel`	Remove label from label definition creator for lidar workflow (Since R2020b)

Load Ground Truth Data Sources

`vision.labeler.loading.MultiSignalSource`	Interface for loading signal data into Lidar Labeler app (Since R2020b)
`vision.labeler.loading.PointCloudSequenceSource`	Load signals from point cloud sequence sources into Lidar Labeler app (Since R2020b)
`vision.labeler.loading.VelodyneLidarSource`	Load signals from Velodyne lidar sources into Lidar Labeler app (Since R2020b)
`lidar.labeler.loading.LasFileSequenceSource`	Load signals from LAS or LAZ file sequence sources into Lidar Labeler app (Since R2020b)
`lidar.labeler.loading.RosbagSource`	Load signals from rosbag sources into Lidar Labeler app (Since R2020b)
`lidar.labeler.loading.CustomPointCloudSource`	Load point cloud data from custom sources into Lidar Labeler app (Since R2021a)

Sync External Image Viewer

`lidar.syncImageViewer.SyncImageViewer`	Interface to connect external tool to Lidar Labeler app (Since R2020b)
`dataSourceChangeListener`	Update external tool when connecting to signal being loaded into Lidar Labeler app (Since R2020b)
`frameChangeListener`	Update external tool when new frame is displayed in Lidar Labeler app (Since R2020b)
`updateLabelerCurrentTime`	Update current time in Lidar Labeler app (Since R2020b)
`close`	Close external tool connected to Lidar Labeler app (Since R2020b)
`disconnect`	Disconnect external tool from Lidar Labeler app (Since R2020b)

Automate Labeling

Action Flags

`initialize`	Initialize state for algorithm execution (optional) (Since R2022a)
`run`	Run label automation on every frame in interval (Since R2022a)
`terminate`	Terminate automated algorithm (optional) (Since R2022a)

Validation

`checkSetup`	Set up validation (optional) (Since R2022a)
`checkSignalType`	Validate signal type (Since R2022a)
`checkLabelDefinition`	Validate label definition (Since R2022a)

Algorithm

`lidar.labeler.AutomationAlgorithm`	Interface for algorithm automation in ground truth labeling (Since R2022a)
`settingsDialog`	Display algorithm settings (optional) (Since R2022a)
`lidar.labeler.mixin.Temporal`	Mixin interface for adding temporal context to automation algorithms (Since R2022a)

Topics

Get Started

Get Started with the Lidar Labeler
Interactively label a point cloud or point cloud sequence.
Keyboard Shortcuts and Mouse Actions for Lidar Labeler
Use keyboard shortcuts and mouse actions to increase productivity while using the Lidar Labeler app.
Use Custom Point Cloud Source Reader for Labeling
Create a reader function to load a custom image data source into the Lidar Labeler.
Connect Image Display to Lidar Labeler
Connect an image display tool to the Lidar Labeler app.

Automate Labeling

Create Automation Algorithm for Labeling
Create a custom automation algorithm to use in a labeling app.
Temporal Automation Algorithms
Create a time-based custom tracking algorithm to import into a labeling app.

Featured Examples

Automate Ground Truth Labeling for Point Cloud Using Pretrained Deep Learning Model

Automate labeling in a point cloud using a pretrained deep learning model in the Lidar Labeler app.

Open Live Script

Automate Ground Truth Labeling for Vehicle Detection Using PointPillars

Automate vehicle detections in a point cloud using a pretrained pointPillarsObjectDetector in the Lidar Labeler app. The example uses the AutomationAlgorithm interface in the Lidar Labeler app to automate labeling.

Open Live Script

Automate Ground Truth Labeling for Lidar Point Cloud Semantic Segmentation Using Lidar Labeler

Automate semantic labeling in a point cloud using a pretrained semantic segmentation network in the Lidar Labeler app. In this example, you can use the AutomationAlgorithm class to automate labeling in the Lidar Labeler app.

Open Live Script