Multi-Layer Modeling of Dense Vegetation from Aerial LiDAR Scans
This work addresses the problem of automated large-scale forestry analysis by providing a dataset and method for multi-layer vegetation modeling, which is incremental as it extends existing LiDAR-based approaches beyond top-of-canopy focus.
The authors tackled the challenge of analyzing multi-layer vegetation structure in wild forests by releasing WildForest3D, a dataset with dense 3D annotations for over 2000 trees across 47,000m², and proposing a 3D deep network that predicts point-wise labels and occupancy rasters, enabling precise layer thickness estimation and watertight meshes for forestry applications.
The analysis of the multi-layer structure of wild forests is an important challenge of automated large-scale forestry. While modern aerial LiDARs offer geometric information across all vegetation layers, most datasets and methods focus only on the segmentation and reconstruction of the top of canopy. We release WildForest3D, which consists of 29 study plots and over 2000 individual trees across 47 000m2 with dense 3D annotation, along with occupancy and height maps for 3 vegetation layers: ground vegetation, understory, and overstory. We propose a 3D deep network architecture predicting for the first time both 3D point-wise labels and high-resolution layer occupancy rasters simultaneously. This allows us to produce a precise estimation of the thickness of each vegetation layer as well as the corresponding watertight meshes, therefore meeting most forestry purposes. Both the dataset and the model are released in open access: https://github.com/ekalinicheva/multi_layer_vegetation.