Segment Anything Meets Urban Remote Sensing: Automated Building and Tree Mapping from UAV Imagery
International Journal of Innovative Science and Research Technology · 18.07.2026 · 293
DOI: 10.38124/ijisrt/26jul153 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 18.07.2026. Verfasst von Reedhi Shukla und 3 weiteren Autor:innen. Die Arbeit nennt 9 Literaturangaben.
Abstract (Originalsprache)
The Segment Anything Model (SAM) has shown very good generalisation across many image types, but when we applied it directly to drone imagery, we found it does not work well — the top-down geometry, spatial scale, and object shapes in aerial data are quite different from the natural images SAM was trained on. Based on this, we designed SAMD (Segment Anything Model for Drone data), which combines a U-Net with a ResNet-34 encoder and SAM into a single pipeline. The U-Net is fine-tuned on drone imagery and produces pixel-wise masks for buildings and trees; these masks are then used as spatial prompts for SAM, which refines the boundaries and converts everything into georeferenced vector shapefiles. Building heights are derived from DSM-DMT differencing, and the final output is a 3D city model rendered in CesiumJS. We tested SAMD on drone imagery of Kanchipuram city, Tamil Nadu, India. Building extraction reached 85% F1 and tree delineation reached 80% F1. SAMD performed better than standalone SAM on drone data and is also slightly better than U-Net alone on boundary precision.
Zitieren
APA
Shukla, R., P., S. K., J., K., & B., N. (2026). Segment Anything Meets Urban Remote Sensing: Automated Building and Tree Mapping from UAV Imagery. International Journal of Innovative Science and Research Technology, 293. https://doi.org/10.38124/ijisrt/26jul153
Vancouver
Shukla R, P. SK, J. K, B. N. Segment Anything Meets Urban Remote Sensing: Automated Building and Tree Mapping from UAV Imagery. International Journal of Innovative Science and Research Technology. 2026:293. doi:10.38124/ijisrt/26jul153
BibTeX
@article{Shukla2026,
author = {Shukla, Reedhi and P., Sampath Kumar and J., Kamini and B., Narender},
title = {Segment Anything Meets Urban Remote Sensing: Automated Building and Tree Mapping from UAV Imagery},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {293},
doi = {10.38124/ijisrt/26jul153}
}
EUVIMED