lllxlll/UC_Merced

---
language: en
license: unknown
task_categories:
- image-classification
paperswithcode_id: uc-merced-land-use-dataset
pretty_name: UC Merced
tags:
- remote-sensing
- earth-observation
- geospatial
- satellite-imagery
- land-cover-classification
- USGS National Map
- USGS
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype:
class_label:
names:
'0': agricultural
'1': airplane
'2': baseballdiamond
'3': beach
'4': buildings
'5': chaparral
'6': denseresidential
'7': forest
'8': freeway
'9': golfcourse
'10': harbor
'11': intersection
'12': mediumresidential
'13': mobilehomepark
'14': overpass
'15': parkinglot
'16': river
'17': runway
'18': sparseresidential
'19': storagetanks
'20': tenniscourt
splits:
- name: train
num_bytes: 438356371.8
num_examples: 2100
download_size: 416445676
dataset_size: 438356371.8
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---

# UC Merced

<!-- Dataset thumbnail -->

<!-- Provide a quick summary of the dataset. -->
The UC Merced Land Use dataset is a land use classification dataset of 2.1k 256x256 1ft resolution RGB images of urban locations around the U.S. extracted from the USGS National Map Urban Area Imagery collection with 21 land use classes (100 images per class).
- **Paper:** https://arxiv.org/abs/1911.06721
- **Homepage:** http://weegee.vision.ucmerced.edu/datasets/landuse.html

## Description

<!-- Provide a longer summary of what this dataset is. -->

- **Total Number of Images**: 2100
- **Bands**: 3 (RGB)
- **Image Size**: 256x256
- **Resolution**: 0.3m
- **Land Cover Classes**: 21
- **Classes**: agricultural, airplane, baseballdiamond, beach, buildings, chaparral, denseresidential, forest, freeway, golfcourse, harbor, intersection, mediumresidential, mobilehomepark, overpass, parkinglot, river, runway, sparseresidential, storagetanks, tenniscourt
- **Source**: USGS

## Usage

To use this dataset, simply use `datasets.load_dataset("blanchon/UC_Merced")`.
<!-- Provide any additional information on how to use this dataset. -->
```python
from datasets import load_dataset
UC_Merced = load_dataset("blanchon/UC_Merced")
```

## Citation

<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
If you use the EuroSAT dataset in your research, please consider citing the following publication:

```bibtex
@article{neumann2019indomain,
title = {In-domain representation learning for remote sensing},
author = {Maxim Neumann and Andre Susano Pinto and Xiaohua Zhai and Neil Houlsby},
year = {2019},
journal = {arXiv preprint arXiv: 1911.06721}
}
```