Keeping pace with a changing planet: An interactive segmentation framework for refining delineations of dynamic Earth features with the Segment Anything Model

Accurate delineations of Earth’s surface features are crucial for environmental science, but for dynamic landscapes like thawing permafrost, these datasets rapidly become outdated and inaccurate. Manual refinement of these outdated labels is prohibitively slow, while existing foundation segmentation...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	Yili Yang, Arav Agarwal, Marlena Bartkus, Heidi Rodenhizer, Wenwen Li, Hyunho Lee, Chia-Yu Hsu, Greg Fiske, Stefano Potter, Anna Liljedahl, Brendan M. Rogers, Susan M. Natali
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	Elsevier 2026-03-01
Serie:	International Journal of Applied Earth Observations and Geoinformation
Ämnen:	Segment Anything Model (SAM) Geospatial AI Zero-shot segmentation Interactive image segmentation Promptable image segmentation Retrogressive thaw slumps
Länkar:	http://www.sciencedirect.com/science/article/pii/S1569843226001032
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!