Manually Labeled TLS Tree Point Clouds for Leaf-Wood Separation, 11 Scans

Weiser, Hannah provides 11 terrestrial laser scanning (TLS) tree point clouds in .LAZ format, manually labeled into leaf and wood points. The dataset covers 7 different tree species and includes additional attributes like Reflectance and Amplitude. It is intended for training and validation of semantic segmentation algorithms, as referenced in Esmorís et al. 2023.

Use Cases

• Training leaf-wood separation models based on manually labeled Classification field (0=wood, 1=leaf).
• Validating point cloud segmentation algorithms based on the provided 11 TLS scans of 7 species.
• Analyzing tree structure using additional point attributes like Reflectance and Amplitude mentioned in the description.
• Normalizing and centering point clouds for comparative studies using the provided tree positions in ETRS89/UTM zone 32N.

Strengths

• Contains 11 manually labeled point clouds, providing ground truth for algorithm development.
• Includes 7 different tree species, suggesting some taxonomic diversity.
• Provides additional point attributes (e.g., Deviation, Reflectance, Amplitude) beyond basic coordinates.
• Point clouds were filtered by Deviation (>50), indicating a quality control step.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

Weiser, Hannah via heiDATA Harvested Dataverse.

Collection Method

Terrestrial laser scanning, manually labeled.

Freshness

Last updated 2024-03-10 10:05:01; freshness should be verified.

Geography

Tree positions provided in ETRS89 / UTM zone 32N (EPSG:25832); specific location not stated.