Classify airborne and mobile mapping LiDAR point clouds with deep learning (LitePT-L); railway and power line models through the author's Cohort.
Classifies airborne and mobile mapping LiDAR point clouds
(LAS / LAZ / COPC) with deep-learning models. Two free classifiers:
Airborne (LitePT-L at 10 cm on NVIDIA GPUs, the UrbanFiltering 3D
SegFormer from NRCan's TreeAIBox on other computers; standard ASPRS
codes) and Mobile mapping (LitePT-L at 5 cm: ground, low and high
vegetation, buildings, pole-like objects, vehicles, fences and
barriers, wires; editable class codes; NVIDIA CUDA GPU required).
The Railway classifier (rails, masts, wires, ground, vegetation,
fences) and the Power lines classifier (power line corridors) are
reserved for the participants of the author's live Cohort; the plugin
shows where to get access.
External dependencies: PyTorch, laspy, lazrs, timm, scipy and, on
NVIDIA GPUs, spconv. A one-click setup installs them into a separate
per-user folder on first use (no admin rights, nothing to
configure), and the model weights download automatically. Files in
feet are converted from their CRS; tiling and streaming handle files
larger than RAM. Model weights are CC BY-NC 4.0 (railway: CC BY-NC-SA 4.0). Documentation:
https://github.com/akharroubi/AerialLidarClassifier
Like the plugin? Help it grow: the author's live Cohort, LiDAR Point
Clouds Processing in QGIS, funds the next models and releases:
https://maven.com/geomatics/qgis3d?utm_source=plugins.qgis.org&utm_medium=listing&utm_campaign=qgis3d
Plugin Tags