Articles | Volume 14, issue 3
https://doi.org/10.5194/esurf-14-391-2026
https://doi.org/10.5194/esurf-14-391-2026
Research article
 | 
12 May 2026
Research article |  | 12 May 2026

OrthoSAM: multi-scale extension of the Segment Anything Model for river pebble delineation from large orthophotos

Vito Chan, Aljoscha Rheinwalt, and Bodo Bookhagen

Viewed

Total article views: 8,961 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
6,676 2,085 200 8,961 275 276
  • HTML: 6,676
  • PDF: 2,085
  • XML: 200
  • Total: 8,961
  • BibTeX: 275
  • EndNote: 276
Views and downloads (calculated since 29 Aug 2025)
Cumulative views and downloads (calculated since 29 Aug 2025)

Viewed (geographical distribution)

Total article views: 8,961 (including HTML, PDF, and XML) Thereof 8,940 with geography defined and 21 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 12 May 2026
Download
Short summary
OrthoSAM is a new method that uses Segment Anything Model (SAM) to automatically identify and outline individual pebbles in high-resolution aerial images. OrthoSAM divides large photos into smaller sections that SAM can process effectively, and it improves the way to tell SAM where to look for objects. It uses a multi-resolution approach to handle different sizes, and it can be used to determine the distribution. Tests with computer-generated images and field data show that it is very precise.
Share