Sign in to view source links and access this dataset
Description
TowerDataset is a power-line corridor point cloud dataset for semantic segmentation. It contains 661 annotated airborne and mobile LiDAR scenes of transmission towers, conductors, insulators, vegetation, and ground objects, totaling 2,466,076,987 points. The dataset was created by author tccx18 and was last updated on Hugging Face in May 2026.
Use Cases
Training semantic segmentation models to identify transmission towers and conductors in LiDAR data.
Developing algorithms for vegetation encroachment detection near power lines based on point cloud classification.
Creating synthetic environments for power-line corridor simulation and autonomous inspection planning.
Benchmarking point cloud segmentation performance on complex infrastructure scenes.
Strengths
Contains 661 total scenes, providing a substantial number of examples for model training and evaluation.
Offers a large-scale point cloud with over 2.4 billion total data points.
Includes a predefined split with 419 training, 122 validation, and 120 test scenes for standardized benchmarking.
Limitations
Column-level documentation is absent; field semantics must be inferred after download.
Geographic and temporal coverage is unspecified, which may limit understanding of data representativeness.
The dataset's license is unknown, which could restrict permissible use cases.
Provenance
Source
huggingface
Collection Method
Likely collected via airborne and mobile LiDAR scanning of power-line corridors.
Time Range
null
Freshness
Last updated 2026-05-07 12:29:08; freshness should be verified.
Geography
null
License is unknown, which is a critical consideration before use.