Create and Export Labels and Label Definitions

After loading the point cloud data into the Lidar Labeler app, create label definitions and attributes. Label definitions contain information about the labels that you can annotate the points with.

For more information on how to load and view data in the Lidar Labeler app, see Load and View Point Cloud Data.

Create an ROI Label Definition

An ROI label is a label that corresponds to a region of interest (ROI).

1. On the ROI Labels tab in the left pane, click Label.

2. Specify the label type as Cuboid, Line, Voxel and provide a name for the label.

   

3. From the Group list, select New Group and provide a name for the group. The group name appears on the ROI Labels tab with the specified label name under it. Adding labels to groups is optional.

4. You can also add a label description.

5. Click OK to create the label definition.

For more details about these labels, see ROI Labels and Attributes.

Tip

To learn to label point cloud data using tutorials within the app, click Tutorials in the Resources section, and select a desired tutorial from these options: Cuboid, Line, Voxel, Smart Voxel, and Voxel Plane.

Create Voxel Label

When you define a Voxel ROI label, the app opens the Voxel tab. You can draw and fine-tune the voxel regions on a point cloud to label them.

 Label Voxel Region

You can manually label a voxel region using these options:

• Brush — To label regions using a paintbrush method, click Brush, and select the desired size of marker using the Marker Size slider. Then, drag the brush over the desired points in the point cloud data. To erase labels, click Brush Erase, adjust the Marker Size slider, and drag the eraser over the desired points. You can also increase or decrease marker size using the Plus (+) or Minus (-) key, respectively.

• Lasso — To label regions by outlining them using a free form lasso, click Lasso, and draw a region of interest (ROI) on the point cloud. To erase labels, click Lasso Erase. Then, draw an ROI on the point cloud.

Use options in the Smart Voxel section for automatic voxel detection. Select Smart Lasso to draw an ROI on the point cloud. The app automatically detects and labels a voxel within the ROI. You can further fine-tune the detected voxel label.

• Click Mark Foreground and mark the points inside the ROI that you want to label. Foreground marks appear in green.

• Click Mark Background and mark the points inside the ROI that you do not want to label. Background marks appear in red.

To remove all marks, click Clear Marks.

 Label Point Clusters

Click Select Cluster to label a cluster of points. You can tune the clustering algorithm by selecting Cluster Settings.

 Label Planar Region

Click Select Plane to label a planar region on the point cloud. You must mark three points that form the plane. You can adjust the thickness of a plane by using the Plane Thickness slider.

 Data Visibility

You can control which data to show or hide in voxel regions on a labeled point cloud using these options:

• Show Labeled Data — Use this option to display only labeled data. When you select this option, the app hides unlabeled data.

• Show Unlabeled Data — Use this option to display only unlabeled data. When you select this option, the app hides labeled data.

• Show Selected Labeled Data — Use this option to display only selected labeled data.

• Shows All Data — Use this option to display all data.

To update the visualization of data after any modification, click Refresh. For example, if you want to focus on unlabeled data for further labeling, first select Show Unlabeled Data. The app displays only unlabeled data. Then, you can label data from the display and click Refresh to hide the newly labeled data and focus on the remaining unlabeled data.

 Voxel Opacity

Use the Voxel Opacity slider to adjust the transparency of the voxel labels for better visualization.

Tip

To undo or redo a labeling action in the Voxel tab, press Ctrl+Z or Ctrl+Y, respectively.

Create ROI Attribute

An ROI attribute specifies additional information about an ROI label. You can define ROI attributes of these types.

• Numeric Value — Specify a numeric scalar attribute, such as the number of doors on a labeled vehicle.

• String — Specify a string scalar attribute, such as the color of a vehicle.

• Logical — Specify a logical true or false attribute, such as whether a vehicle is in motion.

• List — Specify a drop-down list attribute of predefined strings, such as make or model of a vehicle.

Use this process to create an attribute.

1. On the ROI Labels tab in the left pane, select a label and click Attribute.

2. Provide an attribute name and select the attribute type. Optionally, give the attribute a description, and click OK. You can hover over the information icon that appears next to the attribute field to display the added description.

   

For more details about these attributes, see ROI Labels and Attributes.

Create Scene Label Definition

A scene label defines additional information across a scene. Use scene labels to describe conditions, such as lighting and weather, or events, such as lane changes.

Use this process to create a scene label definition.

1. Select the Scene Labels tab in the left pane of the app and click Define new scene label.

2. In the Define new scene label window provide a name for the label.

3. Choose a Color for the label.

   

4. From the Group list, select New Group and provide a name for the group. Adding labels to groups is optional.

5. The Scene Labels pane shows the scene label definition.

Label Data in Burst Mode

Use Burst Mode to label static objects across various point cloud frames at once.

1. In the range slider pane, click Burst Mode to begin labeling data in burst mode.

2. Specify the frame numbers in which you want to label objects. The app displays the specified frames in the visualization pane.

3. Draw labels on static objects. The app applies labels across all specified frames.

4. Verify the drawn labels across the specified point cloud frames and then exit burst mode labeling by selecting Accept and Exit.

Burst mode can be useful when the input data has a large number of frames with static objects.

View and Adjust Labels

Once you have created labels for your point cloud data, the app toolstrip provides options on the LIDAR tab, to view and adjust your point cloud and label data. These options enable you to more easily label sparse 3-D data points.

Projected View

Select Projected View to view the front-view, top-view, and side-view of the selected label simultaneously. Use these views to manually adjust the accuracy of your labels.

Auto Align Labels

Select Auto Align to fit a cuboid accurately to the label data and align the label in the direction of the object. This image shows the difference between a label with and a label without the Auto Align option selected.

Label without Auto Align option	Label with Auto Align option

Snap and Shrink Labels

On the LIDAR tab, use these options to snap and shrink your labels to fit the points.

• Shrink To Fit — Shrink the size of cuboid labels to best fit the labeled points.

• Snap To Cluster — Snap labels to best fit the selected point clusters. You can also specify which clustering algorithm to use to fine-tune the point clusters, by selecting Cluster Settings.

  

  • Select Range-based clustering to cluster point cloud data using the segmentLidarData function. This option is not applicable for unorganized point cloud data.

  • Select Distance-based clustering to cluster point cloud data using the pcsegdist function.

  • Select k-means clustering to perform k-means clustering on the points.

  • Select DBSCAN clustering to cluster point cloud data using a density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm, where each point of a valid cluster must have at least a minimum number of neighboring points within a given radius.

  You can specify the algorithm parameters in the dialog box, and visualize the output point cloud clusters.

• Snap to Point — Snap the line label vertex to the nearest point in the point cloud.

Tip

For more visualization options, see Visualize Point Cloud Data.

Export Labels and Save Labeling Session

After labeling your point cloud data, click Export on the LABEL tab to export the labels. You can export the labels and label definitions to a MAT file or to the MATLAB workspace.

If the point cloud data contains voxel labels, you can export point cloud data and associated classification attributes to a LAS/LAZ file. On the LABEL tab, click Export > To LAS/LAZ File. The app opens the Export Voxel Labels dialog box and populates the default values of the Folder Path and Filename parameters. To export to a different location, click Browse. You can also change the value of Filename parameter. If a file with the specified name already exists, the app overwrites the existing file.

The Export Voxel Labels dialog box also shows the mapping between label definitions of the app and the standard classes of LAS/LAZ file format. To change the mapping of a label definition, select the desired value of the respective LAS/LAZ Standard Classes parameter from the drop-down list.

You can also manage your data by saving and loading app sessions. To save your session, and then reopen it later to continue labeling the same data, on the LABEL tab,

• Select Save Session, and then either Save or Save As, to save the current labeling session.

• Click New Session, in the dialog box that opens, specify a session folder.

• Click Open Session, and select one of the listed recent sessions, or navigate to the folder of a previous session.