{"name": "Aerial LiDAR Classifier", "package_name": "Aerial_LiDAR_Classifier", "description": "Deep-learning semantic segmentation of aerial LiDAR point clouds with a 3D SegFormer model (TreeAIBox / NRCan).", "about": "Classifies aerial LiDAR point clouds (LAS / LAZ / COPC) into\nGround, Vegetation, Building, Wires / Powerlines and Poles\n(standard ASPRS codes) using the UrbanFiltering 3D SegFormer\nmodel from NRCan's TreeAIBox project. Runs on NVIDIA GPU (CUDA),\nApple Silicon (MPS) or CPU; spatial tiling handles files larger\nthan RAM. A one-click installer sets up an isolated Python venv\non first use, with no impact on QGIS's own Python. The model is\ndistributed under CC BY-NC 4.0; full documentation, the GPU\ndriver table and the CLI / Processing usage are on the project\nhomepage: https://github.com/akharroubi/AerialLidarClassifier", "homepage": "https://github.com/akharroubi/AerialLidarClassifier", "repository": "https://github.com/akharroubi/AerialLidarClassifier", "tracker": "https://github.com/akharroubi/AerialLidarClassifier/issues", "author": "Abderrazzaq Kharroubi (GeoScITY Lab, University of Liege)", "tags": ["classification", "lidar", "point cloud", "aerial", "machine learning", "laz", "las", "deep learning", "semantic segmentation", "asprs", "pytorch", "treeaibox", "segformer", "copc"], "downloads": 489, "latest_version": "1.0.2", "versions": [{"version": "1.0.2", "experimental": true, "qgis_min": "3.34.0", "qgis_max": "3.99.0", "downloads": 312, "uploaded_by": "Kharroubi", "upload_datetime": "2026-05-19T09:33:33.089179"}, {"version": "1.0.1", "experimental": true, "qgis_min": "3.34.0", "qgis_max": "3.99.0", "downloads": 80, "uploaded_by": "Kharroubi", "upload_datetime": "2026-05-18T06:18:15.263222"}, {"version": "1.0.0", "experimental": true, "qgis_min": "3.34.0", "qgis_max": "3.99.0", "downloads": 91, "uploaded_by": "Kharroubi", "upload_datetime": "2026-05-12T06:22:12.596750"}]}