Identifying spatial regions where biodiversity is threatened is crucial for effective ecosystem conservation and monitoring. In this stydy, we assessed varios machine learning methods to detect grazing trails automatically. We tested five semantic segmentation models combined with 14 different encoder networks. The best combination was UNet with MambaOut encoder. The solution proposed could be used as the basis for tools aiming at mapping and tracking changes in grazing trails on a continuous temporal basis.
@article{arxiv.2504.12121,
title = {Remote sensing colour image semantic segmentation of trails created by large herbivorous Mammals},
author = {Jose Francisco Diez-Pastor and Francisco Javier Gonzalez-Moya and Pedro Latorre-Carmona and Francisco Javier Perez-Barbería and Ludmila I. Kuncheva and Antonio Canepa-Oneto and Alvar Arnaiz-González and Cesar Garcia-Osorio},
journal= {arXiv preprint arXiv:2504.12121},
year = {2025}
}
Comments
24 pages, 6 figures. Submitted to "International Journal of Remote Sensing"