PatternNet Dataset Overview

Basic Information

• Language: English
• Task Category: Image Classification
• Tags: Remote Sensing, Earth Observation, Geospatial, Satellite Imagery, Land Cover Classification, Google Earth
• Dataset Name: PatternNet

Dataset Details

• Features:

  • image: Image data
  • label: Label data, containing 38 classes
    • Class names: airplane, baseball field, basketball court, beach, bridge, cemetery, chaparral, christmas tree farm, closed road, coastal mansion, crosswalk, dense residential, ferry terminal, football field, forest, freeway, golf course, harbor, intersection, mobile home park, nursing home, oil gas field, oil well, overpass, parking lot, parking space, railway, river, runway, runway marking, shipping yard, solar panel, sparse residential, storage tank, swimming pool, tennis court, transformer station, wastewater treatment plant

• Data Splits:

  • train: Training set, containing 30,400 samples, size 1,422,177,005.0 bytes

• Dataset Size:

  • Download size: 1,422,316,869 bytes
  • Dataset size: 1,422,177,005.0 bytes

Dataset Description

• Total Images: 30,400
• Bands: 3 (RGB)
• Image Resolution: 256×256 pixels
• Land Cover Classes: 38

Usage

• Load dataset: datasets.load_dataset("blanchon/PatternNet")

Citation

• Citation information: bibtex @article{li2017patternnet, title = {PatternNet: Visual Pattern Mining with Deep Neural Network}, author = {Hongzhi Li and Joseph G. Ellis and Lei Zhang and Shih‑Fu Chang}, journal = {International Conference on Multimedia Retrieval}, year = {2017}, doi = {10.1145/3206025.3206039}, bibSource = {Semantic Scholar https://www.semanticscholar.org/paper/e7c75e485651bf3ccf37dd8dd39f6665419d73bd} }