3D Fuel Segmentation Using Terrestrial Laser Scanning and Deep Learning

Documentation for package ‘FuelDeep3D’ version 0.1.1

add_ground_csf	Add a ground class using CSF post-processing
config	Create a FuelDeep3D configuration
ensure_py_env	Ensure a Conda environment and Python dependencies for FuelDeep3D
evaluate_single_las	Evaluate predictions stored in a single LAS/LAZ
evaluate_two_las	Evaluate predictions stored in two LAS/LAZ objects
install_py_deps	Install Python dependencies into a Conda environment (FuelDeep3D)
las_class_distribution	Class distribution summary for a LAS point cloud
plot_3d	Plot a 3D LAS point cloud colored by elevation
plot_confusion_matrix	Plot a confusion matrix heatmap (ggplot2)
predict	Predict fuel classes for a LAS/LAZ file using a pre-trained model
predicted_plot3d	Plot a LAS point cloud in 3D colored by a class field
print_confusion_matrix	Print a confusion matrix (LAS/LAZ or precomputed cm)
print_metrics_table	Print per-class metrics and summary averages
remove_noise_sor	Remove sparse outlier points using Statistical Outlier Removal (SOR)
train	Train the FuelDeep3D model (build NPZ tiles if missing)