About the Dataset

This dataset provides high-resolution satellite imagery collected via drones in the Kenol section of Murang'a, Kenya. The dataset includes both raw drone imagery and labeled imagery intended for building footprint and field boundary segmentation tasks.

• Provided by: @ksa
• Author: Kenya Space Agency

Data Format

The dataset is structured in Cloud Optimized GeoTIFF format, which enables efficient access to large geospatial datasets over the web.

Usage

The dataset is suitable for training and evaluating models for field boundary and building footprint segmentation tasks. The labels are provided in the Labels directory, with building footprints labeled with a class value of 1, and field boundaries labeled with a class value of 2. In the case where building footprint is within field boundary, it has a class value of 3. Every other item not either of the two has a class value of 0.

Image Details

• Image Dimensions: 512 x 512 pixels
• Image Channels: RGBA

License

This dataset is provided under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0). Please read the LICENSE file for more details.

Download Dataset

This dataset can be dowloaded via the ACCESS DATA tab. Labels can be found within the labels sub-directory and imagery can be found within the imagery sub-directory

Citation

If you find this dataset useful in your work, please consider citing it:

@dataset{kenol-section,
  author = {Kenya Space Agency},
  title = {Kenya Building Footprints and Field Boundaries Dataset: This dataset contains satellite imagery collected from drones in Kenol section, Murang'a Kenya. Dataset contains the drone imagery and labelled imagery},
  year = {2023},
  publisher = {Kenya Space Agency},
  howpublished = {\url{https://beta.source.coop/ksa/kenol-section}},
}