1/1
Electric Transmission Infrastructure Satellite Imagery Dataset for Computer Vision
Version 2 2021-07-21, 16:30
Version 1 2021-07-19, 21:59
dataset
posted on 2021-07-21, 16:30 authored by Wei HuWei Hu, Bohao Huang, Kyle BradburyKyle Bradbury, Jordan Malof, Varun NairVarun Nair, Tamasha PathirathnaTamasha Pathirathna, Xiaolan YouXiaolan You, Qiwei HanQiwei Han, Jichen Yang, Artem StreltsovArtem Streltsov, Leslie CollinsThis dataset accompanies the paper, GridTracer: Automatic Mapping of Power Grids using Deep Learning and Overhead Imagery, found at https://arxiv.org/abs/2101.06390. Please see that link for more information (live link below in references).
Overview
This dataset contains fully annotated electric transmission and distribution infrastructure for approximately 264 km2 of high resolution satellite and aerial imagery, spanning 7 cities and 2 countries across 5 continents.
This dataset was designed for training machine learning algorithms to automatically identify electricity infrastructure in satellite imagery; for those working on identifying the best pathways to electrification in low and middle income countries, and for researchers investigating domain adaptation for computer vision.
Additional information on this dataset is available in the Documentation.pdf file included in this dataset.
Data Sources
LINZ: Land Information New Zealand
USGS: United States Geological Survey
Source of imagery tagged as from USGS: U.S. Geological Survey.
Funding
NSF OIA-1937137
Duke University Bass Connections
Duke University Data+
Alfred P. Sloan Foundation via the Duke University Energy Data Analytics Fellows Program
History
Usage metrics
Categories
- Energy generation, conversion and storage (excl. chemical and electrical)
- Electrical engineering not elsewhere classified
- Electrical energy generation (incl. renewables, excl. photovoltaics)
- Computer vision
- Knowledge representation and reasoning
- Image processing
- Artificial intelligence not elsewhere classified
Keywords
Power GridsElectricity Transmission & DistributionEnergyMachine LearningComputer VisionDeep LearningDomain AdaptationEnergy SystemsElectricity InfrastructureEnergy Generation, Conversion and Storage EngineeringPower and Energy Systems Engineering (excl. Renewable Power)Renewable Power and Energy Systems Engineering (excl. Solar Cells)Computer VisionKnowledge Representation and Machine LearningImage ProcessingArtificial Intelligence and Image Processing
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC