Digambar Patil, Sonali und Guo, Qi (2023) Stellar: A Large Satellite Stereo Dataset for Digital Surface Model Generation. In: 39th International Symposium on Remote Sensing of Environment, ISRSE 2023. International Symposium on Remote Sensing of Environment, 2023-04-24 - 2023-04-28, Antalya, Türkei. doi: 10.5194/isprs-archives-XLVIII-M-1-2023-433-2023. ISSN 1682-1750.
![]() |
PDF
12MB |
Kurzfassung
Stellar is a large, satellite stereo dataset. It contains rectified stereo pairs of the terrain captured by the satellite image sensors and corresponding true disparity maps and semantic segmentation. Unlike stereo vision in autonomous driving and mobile imaging, a satellite stereo pair is not captured simultaneously. Thus, the same object in a satellite stereo pair is more likely to have a varied visual appearance. Stellar provides flexible access to such stereo pairs to train methods to be robust to such appearance variation. We use publicly available data sources, and invented several techniques to perform data registration, rectification, and semantic segmentation on the data to build Stellar. In our preliminary experiment, we fine-tuned two deep-learning stereo methods on Stellar. The result demonstrates that most of the time, these methods generate denser and more accurate disparity maps for satellite stereo by fine-tuning on Stellar, compared to without fine-tuning on satellite stereo datasets, or fine-tuning on previous, smaller satellite stereo datasets. Stellar is available to download at https://github.com/guo-research-group/Stellar.
elib-URL des Eintrags: | https://elib.dlr.de/199383/ | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag) | ||||||||||||
Titel: | Stellar: A Large Satellite Stereo Dataset for Digital Surface Model Generation | ||||||||||||
Autoren: |
| ||||||||||||
Datum: | 2023 | ||||||||||||
Erschienen in: | 39th International Symposium on Remote Sensing of Environment, ISRSE 2023 | ||||||||||||
Referierte Publikation: | Ja | ||||||||||||
Open Access: | Ja | ||||||||||||
Gold Open Access: | Nein | ||||||||||||
In SCOPUS: | Ja | ||||||||||||
In ISI Web of Science: | Nein | ||||||||||||
DOI: | 10.5194/isprs-archives-XLVIII-M-1-2023-433-2023 | ||||||||||||
ISSN: | 1682-1750 | ||||||||||||
Status: | veröffentlicht | ||||||||||||
Stichwörter: | Photogrammetry, digital surface model, big data challenge, digital earth, computationally intensive data processing. | ||||||||||||
Veranstaltungstitel: | International Symposium on Remote Sensing of Environment | ||||||||||||
Veranstaltungsort: | Antalya, Türkei | ||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||
Veranstaltungsbeginn: | 24 April 2023 | ||||||||||||
Veranstaltungsende: | 28 April 2023 | ||||||||||||
Veranstalter : | ISPRS | ||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||
HGF - Programmthema: | Technik für Raumfahrtsysteme | ||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||
DLR - Forschungsgebiet: | R SY - Technik für Raumfahrtsysteme | ||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Digitale Transformation in der Raumfahrt [SY], D - Digitaler Atlas 2.0 | ||||||||||||
Standort: | Braunschweig | ||||||||||||
Institute & Einrichtungen: | Institut für Softwaretechnologie | ||||||||||||
Hinterlegt von: | Digambar Patil, Sonali | ||||||||||||
Hinterlegt am: | 08 Dez 2023 13:07 | ||||||||||||
Letzte Änderung: | 24 Apr 2024 20:59 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags