Abstract Semantic segmentation of point clouds using deep learning (DL) has been the subject of research in forestry in recent years due to its potential applications. Several scientific and management disciplines, such as biodiversity monitoring, ecosystem carbon assessments, or forest management could benefit from this technique. However, it requires manual segmentation of point clouds to be used as training data. This process is highly labour-intensive and time-consuming, and there is a notable lack of publicly available datasets to support the development of accurate DL semantic segmentation models for forestry and forest ecology applications. Here, we present SegmentedForests, a curated dataset of manually segmented ground-based point clouds from forest plots, specifically designed to facilitate the training and validation of semantic segmentation models. This publicly available dataset contains 920 million labelled points from 14 forest plots, acquired using both terrestrial laser scanning (TLS) and mobile laser scanning (MLS) technologies. It covers two hectares of broadleaf, conifer, and mixed stands from different bioclimatic regions and features 1600 trees across 16 tree species. Each point cloud is labelled into multiple vegetation classes (up to 16), such as tree stems, branches, grass, shrubs, and down wood, as well as non-vegetation elements commonly present in forest scenes, including rocks, people, and stakes. Data splits to facilitate DL model development using our dataset are provided as well. By releasing this annotated dataset, we seek to address the critical need for publicly available, high-quality training data for DL models that perform semantic segmentation of ground-based point clouds in forest ecosystems.
Laiño et al. (2025) studied this question.