Deep learning-based segmentation of skid trails from airborne LiDAR data
TrailScan is a QGIS plugin for mapping skid trails from Airborne Laser Scanning (ALS) data in forests in Germany. Input: ALS point clouds (.laz or .las) from aircraft, helicopters, or UAVs. Workflow: (1) Preprocessing: Convert the point cloud into a normalized 4-band raster (DTM, CHM, MRM, VDI). (2) Inference: Apply the TrailScan model to the normalized raster to generate a probability raster (0–1) named 'Trailmap'. The trained TrailScan model is available at https://doi.org/10.25625/GEIP6T. Output: Georeferenced raster 'Trailmap' ready for further GIS analyses.
Plugin Tags