Manually labeled terrestrial laser scanning point clouds of individual trees for leaf-wood separation

This dataset contains 11 terrestrial laser scanning (TLS) tree point clouds (in .LAZ format v1.4) of 7 different species, which have been manually labeled into leaf and wood points. The labels are contained in the Classification field (0 = wood, 1 = leaf). The point clouds have additional attributes (Deviation, Reflectance, Amplitude, GpsTime, PointSourceId, NumberOfReturns, ReturnNumber). Before labeling, all point clouds were filtered by Deviation, discarding all points with a Deviation greater than 50. An ASCII file with tree species and tree positions (in ETRS89 / UTM zone 32N; EPSG:25832) is provided, which can be used to normalize and center the point clouds. This dataset is intended to be used for training and validation of algorithms for semantic segmentation (leaf-wood separation) of TLS tree point clouds, as done by Esmorís et al. 2023 (Related Publication). The point clouds are a subset of a larger dataset, which is available on PANGAEA (Weiser et al. 2022b, see Related Dataset). More details on data acquisition and processing, file formats, and quality assessments can be found in the corresponding data description paper (Weiser et al. 2022a, see Related Material).本数据集包含11组覆盖7个不同树种的地面激光扫描（Terrestrial Laser Scanning，简称TLS）树木点云数据，格式为.LAZ v1.4，所有点云已被人工标注为叶片点与木质点。标注信息存储于Classification字段中（0代表木质点，1代表叶片点）。该点云数据包含额外属性字段：偏差值（Deviation）、反射率（Reflectance）、振幅（Amplitude）、GPS时间（GpsTime）、点源ID（PointSourceId）、总返回次数（NumberOfReturns）、当前返回次数（ReturnNumber）。标注前，所有点云已通过偏差值进行滤波处理，剔除了偏差值大于50的所有点。本数据集附带一份ASCII格式文件，记录了树木种类与树木位置信息（坐标系为ETRS89 / UTM第32N带；EPSG:25832），可用于对点云数据进行归一化与中心化处理。本数据集旨在用于训练与验证地面激光扫描树木点云的语义分割（叶片-木质分离）算法，相关研究可参考Esmorís等人2023年发表的相关文献（Related Publication）。本次点云数据为某大型数据集的子集，该完整数据集可在PANGAEA平台获取（Weiser等人2022b，详见相关数据集）。有关数据采集与处理、文件格式以及质量评估的更多细节，可查阅对应的数据集描述论文（Weiser等人2022a，详见相关资料）。