Classification
Fast and accurate point cloud classification.
Flai excels in point cloud classification with pre-trained AI models spanning 19 categories for general mapping, 6 for forestry, and 21 for mobile mapping. In-house retraining ensures adaptability, especially in identifying challenging non-ground classes, reducing manual cleanup efforts.
You have the option to choose from four distinct pre-trained classification models:
✔ Aerial Mapping AI model,
✔ Forestry AI Model
✔ Mobile Mapping AI Model
✔ Indoor Stockpile AI Model
✔ Thin Ground AI model
Depending on the selected Aerial Mapping AI model, the following categories are available:
✔ Other (All man-made objects not part of other categories)
✔ Ground
✔ Vegetation
✔ Buildings
✔ Low isolated noise
✔ Water
✔ Wires (low voltage, high voltage)
✔ Powerline towers (low voltage, high voltage)
✔ Railroad wires and towers
✔ Bridges
✔ High isolated noise
✔ Roof objects (chimneys, antennas, solar panels)
✔ Vehicles
✔ Walls / Facades
✔ Low points
✔ Fences
The following classes can be extracted using the Forestry AI model:
✔ Ground
✔ Vegetation
✔ Tree trunks
✔ Fallen trees
Mobile Mapping AI model outputs the following categories:
✔ Other
✔ Roads
✔ Sidewalks
✔ OtherGround
✔ Traffic Islands
✔ Buildings
✔ Trees and
✔ Traffic lights and Traffic signs
✔ Masts
✔ Wires
✔ Pedestrian
✔ Mobile and Stationary Vehicles
✔ Noise
And two classes output for Indoor stockpile AI models:
✔ Stockpile
✔ Other (All man-made objects not part of other categories)
The Thin Ground AI model can be utilized to refine the ground classification from any AI model. The model lets you specify the output of the retaining Ground and filter other points.
