Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area Delineation

In crisis management and remote sensing, image segmentation plays a crucial role, enabling tasks like disaster response and emergency planning by analyzing visual data. Neural networks are able to analyze satellite acquisitions and determine which areas were affected by a catastrophic event. The pro...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniele Rege Cambrin, Luca Colomba, Paolo Garza
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10980409/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849732124383379456
author Daniele Rege Cambrin
Luca Colomba
Paolo Garza
author_facet Daniele Rege Cambrin
Luca Colomba
Paolo Garza
author_sort Daniele Rege Cambrin
collection DOAJ
description In crisis management and remote sensing, image segmentation plays a crucial role, enabling tasks like disaster response and emergency planning by analyzing visual data. Neural networks are able to analyze satellite acquisitions and determine which areas were affected by a catastrophic event. The problem in their development in this context is the data scarcity and the lack of extensive benchmark datasets, limiting the capabilities of training large neural network models. In this article, we propose a novel methodology, namely Magnifier, to improve segmentation performance with limited data availability. The Magnifier methodology is applicable to any existing encoder–decoder architecture, as it extends a model by merging information at different contextual levels through a dual-encoder approach: a local and global encoder. Magnifier analyzes the input data twice using the dual-encoder approach. In particular, the local and global encoders extract information from the same input at different granularities. This allows Magnifier to extract more information than the other approaches given the same set of input images. Magnifier improves the quality of the results of +2.65% on average intersection over union while leading to a restrained increase in terms of the number of trainable parameters compared to the original model. We evaluated our proposed approach with state-of-the-art burned area segmentation models, demonstrating, on average, comparable or better performances in less than half of the giga floating point operations per second (GFLOPs).
format Article
id doaj-art-08d42909012e42e3ac1c38cc126cc8f6
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-08d42909012e42e3ac1c38cc126cc8f62025-08-20T03:08:20ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118122631227710.1109/JSTARS.2025.356581910980409Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area DelineationDaniele Rege Cambrin0https://orcid.org/0000-0002-5067-2118Luca Colomba1https://orcid.org/0000-0003-2911-4522Paolo Garza2https://orcid.org/0000-0002-1263-7522Politecnico di Torino, Turin, ItalyPolitecnico di Torino, Turin, ItalyPolitecnico di Torino, Turin, ItalyIn crisis management and remote sensing, image segmentation plays a crucial role, enabling tasks like disaster response and emergency planning by analyzing visual data. Neural networks are able to analyze satellite acquisitions and determine which areas were affected by a catastrophic event. The problem in their development in this context is the data scarcity and the lack of extensive benchmark datasets, limiting the capabilities of training large neural network models. In this article, we propose a novel methodology, namely Magnifier, to improve segmentation performance with limited data availability. The Magnifier methodology is applicable to any existing encoder–decoder architecture, as it extends a model by merging information at different contextual levels through a dual-encoder approach: a local and global encoder. Magnifier analyzes the input data twice using the dual-encoder approach. In particular, the local and global encoders extract information from the same input at different granularities. This allows Magnifier to extract more information than the other approaches given the same set of input images. Magnifier improves the quality of the results of +2.65% on average intersection over union while leading to a restrained increase in terms of the number of trainable parameters compared to the original model. We evaluated our proposed approach with state-of-the-art burned area segmentation models, demonstrating, on average, comparable or better performances in less than half of the giga floating point operations per second (GFLOPs).https://ieeexplore.ieee.org/document/10980409/Deep learningearth observation (EO)natural hazard managementpostwildfire segmentationsemantic segmentation
spellingShingle Daniele Rege Cambrin
Luca Colomba
Paolo Garza
Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area Delineation
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning
earth observation (EO)
natural hazard management
postwildfire segmentation
semantic segmentation
title Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area Delineation
title_full Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area Delineation
title_fullStr Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area Delineation
title_full_unstemmed Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area Delineation
title_short Magnifier: A Multigrained Neural Network-Based Architecture for Burned Area Delineation
title_sort magnifier a multigrained neural network based architecture for burned area delineation
topic Deep learning
earth observation (EO)
natural hazard management
postwildfire segmentation
semantic segmentation
url https://ieeexplore.ieee.org/document/10980409/
work_keys_str_mv AT danieleregecambrin magnifieramultigrainedneuralnetworkbasedarchitectureforburnedareadelineation
AT lucacolomba magnifieramultigrainedneuralnetworkbasedarchitectureforburnedareadelineation
AT paologarza magnifieramultigrainedneuralnetworkbasedarchitectureforburnedareadelineation