RT info:eu-repo/semantics/article
T1 Remote sensing colour image semantic segmentation of large herbivorous mammal trails
A1 Diez Pastor, José Francisco
A1 González Moya, Francisco Javier
A1 Latorre Carmona, Pedro
A1 Pérez-Barbería, Francisco Javier
A1 Kuncheva, Ludmila I. .
A1 Canepa Oneto, Antonio Jesús
A1 Arnaiz González, Álvar
A1 García Osorio, César
K1 Semantic segmentation
K1 Deep learning
K1 Grazing trails
K1 Herbivory
K1 Biodiversity
K1 Monitoring
K1 Pastoreo
K1 Grazing
K1 Biodiversidad-Conservación
K1 Biodiversity conservation
K1 Teledetección
K1 Remote sensing
AB Detection of spatial areas where biodiversity is at risk is of paramount importance for the conservation and monitoring of ecosystems. Large terrestrial mammalian herbivores are keystone species as their activity not only has deep effects on soils, plants, and animals but also shapes landscapes, as large herbivores act as allogenic ecosystem engineers. One key landscape feature that indicates intense herbivore activity and potentially impacts biodiversity is the formation of grazing trails. Grazing trails are formed by the continuous trampling activity of large herbivores that can produce complex networks of tracks of bare soil. Here, we evaluated different algorithms based on machine learning techniques to identify grazing trails. Our goal is to automatically detect potential areas with intense herbivory activity, which might be beneficial for conservation and management plans. We have applied five semantic segmentation methods combined with fourteen encoders aimed at mapping grazing trails on aerial images. Our results indicate that in most cases the chosen methodology successfully mapped the trails, although there were a few instances where the actual trail structure was underestimated. The UNet architecture with the MambaOut encoder was the best architecture for mapping trails. The proposed approach could be applied to develop tools for mapping and monitoring temporal changes in these landscape structures to support habitat conservation and land management programmes. This is the first time, to the best of our knowledge, that competitive image segmentation results are obtained for the detection and delineation of trails of large herbivorous mammals.Footnote
PB Taylor and Francis
SN 0143-1161
YR 2026
FD 2026-02
LK https://hdl.handle.net/10259/11881
UL https://hdl.handle.net/10259/11881
LA eng
NO This work was supported by the Asturias Biodiversity Complementary Program BIO06 (Next Generation EU/PRTR), Strategic Projects Oriented Towards Ecological and Digital Transition (TED2021-131388B-100), Spanish Knowledge Generation Projects (PID2023-146074OB-I00) funded by EU Next Generation and Spanish Research Agency, Spanish Research Council Tenured Scientist Incorporation Grants 2022 (202230I041)
DS Repositorio Institucional de la Universidad de Burgos
RD 02-jul-2026