Pointcloud labeling for training

This page is about labeling pointcloud to serve custom AI-training jobs and create detectors to be used in the Analysis Engine.

1. Create a trajectory file that will be used as a canvas to easily navigate through the scene and label all elements of interest
   • Drag & drop your mapping run
   • Create a vector resource for trajectory
   • Copy trajectory file in installation folder
   • Define trajectory as linear reference and lock it

1. Create an asset class that will be labeled (e.g: pylons)
2. Select pointcloud to attribute to an asset object
3. Generate consolidated classified pointcloud + assets to serve AI-detector training
4. Pointcloud selection to classification