Saved in:
Bibliographic Details
Main Authors: Diez-Pastor, Jose Francisco, Gonzalez-Moya, Francisco Javier, Latorre-Carmona, Pedro, Perez-Barbería, Francisco Javier, Kuncheva, Ludmila I., Canepa-Oneto, Antonio, Arnaiz-González, Alvar, Garcia-Osorio, Cesar
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.12121
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916741579276288
author Diez-Pastor, Jose Francisco
Gonzalez-Moya, Francisco Javier
Latorre-Carmona, Pedro
Perez-Barbería, Francisco Javier
Kuncheva, Ludmila I.
Canepa-Oneto, Antonio
Arnaiz-González, Alvar
Garcia-Osorio, Cesar
author_facet Diez-Pastor, Jose Francisco
Gonzalez-Moya, Francisco Javier
Latorre-Carmona, Pedro
Perez-Barbería, Francisco Javier
Kuncheva, Ludmila I.
Canepa-Oneto, Antonio
Arnaiz-González, Alvar
Garcia-Osorio, Cesar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12121
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Remote sensing colour image semantic segmentation of trails created by large herbivorous Mammals
Diez-Pastor, Jose Francisco
Gonzalez-Moya, Francisco Javier
Latorre-Carmona, Pedro
Perez-Barbería, Francisco Javier
Kuncheva, Ludmila I.
Canepa-Oneto, Antonio
Arnaiz-González, Alvar
Garcia-Osorio, Cesar
Computer Vision and Pattern Recognition
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.
title Remote sensing colour image semantic segmentation of trails created by large herbivorous Mammals
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.12121