TBC 2023.10 Train Custom Classification Models

This video highlights the new “Train Custom Classification Models” command in TBC Point Clouds - Extract Classification Point Cloud Regions. Use the Training tab in the Extract Classified Point Cloud Regions command pane to create custom point cloud classification models you can use to automatically extract new point cloud regions and/or adjust existing automatically extracted point cloud regions to your specific data. You do this by providing manually corrected classified region examples (for example, fire hydrants or electrical boxes) to train and validate the model yourself using deep-learning technology, resulting in an output model with the highest quality possible based on your input sample data. To use the custom model, simply select it in the Classification type drop-down list on the Classification tab in the Extract Classified Point Cloud Regions command pane. Prerequisites:
See Licensed Features to determine if your license supports this feature.
An NVIDIA GPU with a minimum of 6 GB of VRAM
One or more LAS (.las) point cloud files containing one or more correctly classified regions (with assigned classification numbers) that represent the classes for which you want to train the new model. (See steps 4 and 5 below.) All files must be stored in the same folder. If multiple regions are created, each one must have a unique classification number. It is recommended that you set the default/unclassified region as classification 0.
For best results, it is important that class objects in the training and validation files be as distinguishable as possible (for example, poles and electrical boxes).
Need demo datasets? Visit https://geospatial.trimble.com/trimbl....
For questions, contact your local Trimble representatives and distributors. Find them here: https://geospatial.trimble.com/where-...
Geospatial: https://geospatial.trimble.com/produc...
Construction: https://construction.trimble.com/prod...