Satellite Stereo Pipeline
Scientific referent
Presentation
The Satellite Stereo Pipeline (S2P) is a processing chain developed at the Centre Borelli, in collaboration with the Centre National d'Etudes Spatiales (CNES), that automatically reconstructs 3D information from pairs of stereo images taken by satellite.
S2P is implemented in an open source Python package that can be used as a Python library and as a command line tool. It produces digital elevation models from images taken by high resolution optical satellites such as Pléiades, WorldView, QuickBird, Spot, Ikonos, or SkySat. It generates 3D point clouds and digital surface models from stereo pairs (two images) or tri-stereo sets (three images) fully automatically. The processing can be applied to an arbitrarily sized region of interest or to the entire images. If necessary, S2P slices the region of interest into several small tiles and processes them in parallel.
The S2P algorithm chain was used in 2016 to win the multi-view stereo 3D mapping competition organized by the Intelligence Advanced Research Projects Activity (IARPA). It is currently used by several public and industrial actors (Kayrros, NamR, MBDA, CNES), and was used as a model for the design of the ground segment of the future CO3D.
Bibliography
- Cours du master MVA. Remote sensing data: from sensor to large-scale geospatial data exploitation Gabriele Facciolo, Carlo de Franchis and Enric Meinhardt-Llopis
- Minitutorial on Automated 3D reconstruction from satellite images, Gabriele Facciolo, Carlo de Franchis and Enric Meinhardt-Llopis, SIAM Conference on Imaging Science, Bologna – Italy. June 5-8 2018.
- Automatic 3D Reconstruction from Multi-Date Satellite Images, Gabriele Facciolo, Carlo de Franchis, and Enric Meinhardt. Earth Vision Workshop CVPR, 2017.
- An automatic and modular stereo pipeline for pushbroom images, Carlo de Franchis, Enric Meinhardt-Llopis, Julien Michel, Jean-Michel Morel, Gabriele Facciolo. ISPRS Annals 2014.
- On Stereo-Rectification of Pushbroom Images, Carlo de Franchis, Enric Meinhardt-Llopis, Julien Michel, Jean-Michel Morel, Gabriele Facciolo. ICIP 2014.
- Automatic sensor orientation refinement of Pléiades stereo images, Carlo de Franchis, Enric Meinhardt-Llopis, Julien Michel, Jean-Michel Morel, Gabriele Facciolo. IGARSS 2014.
