Point cloud classification

Perform semantic segmentation (classification) of LiDAR point clouds using AI models. With dynamic classification you can select desierd categories you would like to classify in your data.

You can choose pre-trained AI models derived from semantic segmentation datasets that are continuously labelled by a team of experts in the geospatial and forestry domain.

You have the option to choose from four distinct classification models:

• Geospatial AI (geoAI) model,

• Forestry AI Model

• Mobile Mapping AI Model

• Indoor Stockpile AI Model

Depending on the selected geospatial AI (geoAI) 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 output the following categories:

• Other

• Roads

• Sidewalks

• OtherGround

• Traffic Islands

• Buildings

• Trees and

• Traffic lights nd Traffic signs

• Masts

• Wires

• Pedestrian

• Mobial and Stationary Vehicles

• Noise

And two classes ouput for Indoor stockpile AI model:

• Stockpile

• Other (All man-made object not part of other categories)

If you notice areas where the AI model does not perform optimally, use Tools for manual annotation directly on Flai's cloud-based machine learning platform.

Annotation-as-a-service is available if you would like us to do data labelling and annotation services to improve the quality and applicability of the AI model.

Learn how to classify your data in blog posts Automatic point cloud classification with Flai web app and Enhance Your Workflow with Flai's Processing Flow Templates