<div align="center"> <a target="_blank" href="https://github.com/CNES/cars"> <picture> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/cars_picto.svg" alt="CARS" width="50%" /> </picture> </a> <h4>CARS, a satellite multi view stereo framework </h4>

<p> <a href="#overview">Overview</a> • <a href="#quick-start">Quick Start</a> • <a href="#documentation">Documentation</a> • <a href="#license">License</a> • <a href="#contribution">Contribution</a> • <a href="#help">Help</a> • <a href="#credits">Credits</a> • <a href="#contact">Contact</a> • <a href="#references">References</a> </p> </div>

🌐 Overview

<div align="center"> <table style="display: inline-block;"> <tr> <td align="center"> <div style="font-size:2em; margin-bottom:10px;"><strong>🎞️ From Stereo Images</strong></div><br> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/animation_sat.gif" alt="Stereo images animation" width="95%"><br> <em>Input stereo image pairs</em> </td> <td align="center"> <div style="font-size:2em; margin-bottom:10px;"><strong>🌍 To Digital Surface Model (DSM)</strong></div><br> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/overview_dsm_3d.gif" alt="DSM overview" width="95%"><br> <em>Output 3D surface reconstruction</em> </td> </tr> </table> </div>

CARS is an open source 3D tool dedicated to produce Digital Surface Models from satellite imaging by photogrammetry. This Multiview Stereo framework is intended for massive DSM production with a robust, performant and modular design.

CARS is currently under active development and integrated into various projects & missions:

<div align="center"> <p align="center"> <a href="https://co3d.cnes.fr/en/co3d-0" target="_blank"> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/logo_co3D_cnes.png" alt="CO3D project" height="70"> </a> &nbsp;&nbsp;&nbsp;&nbsp; <a href="https://www.ai4geo.eu" target="_blank"> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/logo-ai4geo.png" alt="AI4GEO project" height="75"> </a> &nbsp;&nbsp;&nbsp;&nbsp; <a href="https://www.evo-land.eu" target="_blank"> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/logo-evoland.png" alt="Evoland project" height="60"> </a> </p> </div> <br>

Its roadmap and implemented functionalities are evolving regularly depending on specific project requirements.

🚀 Quick start

△ On the way to the Pyramids...

---

You want to build the pyramids by yourself?

<div align="center"> <table style="display: inline-block;"> <tr> <td align="center"> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/dsm.png" alt="Dsm" width="400"><br> </td> <td align="center"> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/clr.png" alt="Color" width="400"><br> </td> <td align="center"> <img src="https://raw.githubusercontent.com/CNES/cars/master/docs/source/images/dsm_clr.png" alt="Color" width="400"><br> </td> </tr> </table> </div>

Download our open licence Pleiades data sample to give CARS a try!

🐋 with Docker

---

🛠 Installation

CARS is available on Docker Hub and can be downloaded by:

docker pull cnes/cars

⚙ Run CARS

You only need to launch one command:

docker run -w /data -v "$(pwd)"/data_gizeh:/data cnes/cars /data/configfile.yaml

🐍 with pip

---

🛠 Installation

CARS can also be downloaded using the pip install command:

pip install cars 

⚙ Run CARS

Once you moved to the data_gizeh directory:

cars configfile.yaml

📚 Documentation

Go to CARS Main Documentation.

📜 License

CARS is licensed under Apache License v2.0. Please refer to the LICENSE file for more details.

🤝 Contribution

To do a contribution, see the Contribution Guide. For project evolution, see Changelog.

🆘 Help

For issues, questions, or feature requests, please open an issue on our GitHub Issues page or check the documentation for additional resources.

You can also ask your questions on the corresponding slack.

✒️ Credits

If you use CARS in your research, please cite the following paper:

@INPROCEEDINGS{9324020,
  author={Youssefi, David and Michel, Julien and Sarrazin, Emmanuelle and Buffe, Fabrice and Cournet, Myriam and Delvit, Jean-Marc and L'Helguen, Céline and Melet, Olivier and Emilien, Aurélie and Bosman, Julien},
  booktitle={IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium}, 
  title={CARS: A Photogrammetry Pipeline Using Dask Graphs to Construct A Global 3D Model}, 
  year={2020},
  volume={},
  number={},
  pages={453-456},
  keywords={Automobiles;Geometry;Three-dimensional displays;Computational modeling;Estimation;Stereo image processing;Task analysis;Image processing;Photogrammetry;Stereovision;Digital Surface Model;High Performance Computing;Cloud Computing;Dask},
  doi={10.1109/IGARSS39084.2020.9324020}}

See Authors file

✉️ Contact

You can contact us on the following mail adress: cars@cnes.fr

🔗 References

• Youssefi D., Michel, J., Sarrazin, E., Buffe, F., Cournet, M., Delvit, J., L’Helguen, C., Melet, O., Emilien, A., Bosman, J., 2020. Cars: A photogrammetry pipeline using dask graphs to construct a global 3d model. IGARSS - IEEE International Geoscience and Remote Sensing Symposium.
• Michel, J., Sarrazin, E., Youssefi, D., Cournet, M., Buffe, F., Delvit, J., Emilien, A., Bosman, J., Melet, O., L’Helguen, C., 2020. A new satellite imagery stereo pipeline designed for scalability, robustness and performance. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.