RT Journal Article
T1 Attention-Based Convolutional Neural Network for Anomaly Detection in Multispectral Images of Semi-Natural Ecosystems
A1 López Fandiño, Javier
A1 Ordóñez Iglesias, Álvaro
A1 Quesada Barriuso, Pablo
A1 Suárez Garea, Jorge Alberto
A1 Argüello Pedreira, Francisco
A1 Blanco Heras, Dora
AB The monitoring of semi-natural ecosystems has become increasingly critical due to the rising impact of ecological disturbances, including natural disasters and unauthorized human-made constructions. Anomaly detection (AD) in multispectral imagery serves as a fundamental tool in this context. Deep-learning (DL)-based techniques are particularly effective at capturing the intricate spectral and spatial patterns of anomalies. This letter proposes a new AD technique called attention-based convolutional neural network (ACNN), designed to enhance AD performance in multispectral images of high spatial resolution for the detection of human-made constructions. The model integrates attention mechanisms to prioritize informative features while suppressing irrelevant background information, thereby improving sensitivity to subtle and rare anomalies. Experimental results on multispectral datasets from semi-natural ecosystems show that the proposed approach outperforms existing DL techniques in terms of detection accuracy. These findings highlight the potential of attention-based models as a robust framework for environmental monitoring and AD in complex remote sensing scenarios.
PB IEEE
SN 1558-0571
YR 2025
FD 2025-06-09
LK https://hdl.handle.net/10347/43138
UL https://hdl.handle.net/10347/43138
LA eng
NO J. López-Fandiño, Á. Ordóñez, P. Quesada-Barriuso, A. S. Garea, F. Argüello and D. B. Heras, "Attention-Based Convolutional Neural Network for Anomaly Detection in Multispectral Images of Semi-Natural Ecosystems," in IEEE Geoscience and Remote Sensing Letters, vol. 22, pp. 1-5, 2025, Art no. 2504005, doi: 10.1109/LGRS.2025.3577943
NO This work was supported in part by MCIN/AEI/10.13039/501100011033 under Grant PID2022–141623NB–I00 and Grant TED2021–130367B–I00; in part by European Union NextGenerationEU/PRTR; in part by the Xunta de Galicia—Consellerıa de Educacion, Ciencia, Universidades e Formacion Professional through the Centro de Investigacion de Galicia Accreditation under Grant 2024-2027 ED431G-2023/04 and the Reference Competitive Group Accreditation under Grant ED431C-2022/16; and in part by ERDF/EU.
DS Minerva
RD 29 abr 2026