streetscapes is a package to extract metadata, download, segment and analyse street view images from various open sources, such as Mapillary, Kartaview and Amsterdam Open Panorama. The package also builds upon the Global Streetscapes, making it possible to use the dataset for analysis and download images with certain properties.
This package is a subproject of (Urban-M4), which aims to model the Urban Heat Island effect by evaluating the properties of individual objects in the images (such as buildings, roads and sidewalks).
For more information, please refer to the documentation.
Create and activate a virtual environment using the tool of your choice, such as venv. You can also use Conda (or Mamba) if you prefer, but please note that all dependencies are installed by pip from PyPI.
Using venv:
python -m venv .venv
source .venv/bin/activateUsing conda:
conda create -n myenv -c conda-forge python=3.12 pip
conda activate myenvThe streetscapes package can be installed from PyPI:
pip install streetscapesAlternatively, the in-development version of streetscapes can be installed by cloning the repository and installing the package locally with pip:
git clone git@github.com:Urban-M4/streetscapes.git
cd streetscapes
pip install -e .streetscapes itself specifies only the minimal required Python verion, some dependencies might be slow to make releases for the latest Python version.
To install with optional dependencies:
git clone git@github.com:Urban-M4/streetscapes.git
cd streetscapes
pip install -e .[dev]The streetscapes project documentation is based on MkDocs. To build and view the documentation:
mkdocs buildThe documentation can then be viewed locally:
mkdocs serveThis will start an HTTP server which can be accessed by visiting http://127.0.0.1:8000 in a browser.
To facilitate the use of streetscapes when dowloading images, access tokens can be added to an .env file in the root directory of the streetscapes repository. You can get and access token for Mapillary here.
| Variable | Description |
|---|---|
MAPILLARY_TOKEN |
A Mapillary token string used for authentication when querying Mapillary via their API. |
If you want to contribute to the development of streetscapes, have a look at the contribution guidelines.
streetscapes is licensed under CC-BY-SA-4.0.
This repository uses the data and work from the Global Streetscapes project.
[1] Hou Y, Quintana M, Khomiakov M, Yap W, Ouyang J, Ito K, Wang Z, Zhao T, Biljecki F (2024): Global Streetscapes — A comprehensive dataset of 10 million street-level images across 688 cities for urban science and analytics. ISPRS Journal of Photogrammetry and Remote Sensing 215: 216-238. doi:10.1016/j.isprsjprs.2024.06.023
The streetscapes package can be cited using the supplied citation information. For reproducibility, you can also cite a specific version by finding the corresponding DOI on Zenodo.