Export Lidar Labels for training neural network

4 views (last 30 days)
Good day,
Is it possible to export the Lidar labels or the labelled files from the Lidar Toolbox to open them with Python?
The goal is to use the labels in Python as training and test data to create a neural network that recognises people in 3D Lidar point clouds.
Is there a similar example?

Answers (1)

Smit
Smit on 9 Feb 2023
Hi,
I understand you want to export Lidar labels generated in MATALB so you can use them in Python.
You may be able to export the label data using functions like “writetimetable”, and the label definitions in a JSON file using “jsonencode” function. An example of this could be
data = groundTruthLidar(dataSource,labelDefs,lidarData);
% Write label definitions in a JSON file
jsonText = jsonencode(data.LabelDefinitions);
writelines(jsonText, 'LabelDefinitions.json');
% Write label data in Excel file
writetimetable(data.LabelData, 'LabelData.xlsx');
You can then use appropriate Python libraries to import this data in your Python code.
You could also possibly use the Lidar Labeler app in MATLAB to export labels. You can open the app using the following command
lidarLabeler;
You can visit the documentation page for more information.
Hope this helps!

Categories

Find more on Labeling, Segmentation, and Detection in Help Center and File Exchange

Products


Release

R2022a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!