Progressive Cross Attention Network for Flood Segmentation using Multispectral Satellite Imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feliren, Vicky, Khikmah, Fithrothul, Bhaswara, Irfan Dwiki, Nasution, Bahrul I., Lechner, Alex M., Saputra, Muhamad Risqi U.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915113053716480
author Feliren, Vicky
Khikmah, Fithrothul
Bhaswara, Irfan Dwiki
Nasution, Bahrul I.
Lechner, Alex M.
Saputra, Muhamad Risqi U.
author_facet Feliren, Vicky
Khikmah, Fithrothul
Bhaswara, Irfan Dwiki
Nasution, Bahrul I.
Lechner, Alex M.
Saputra, Muhamad Risqi U.
contents In recent years, the integration of deep learning techniques with remote sensing technology has revolutionized the way natural hazards, such as floods, are monitored and managed. However, existing methods for flood segmentation using remote sensing data often overlook the utility of correlative features among multispectral satellite information. In this study, we introduce a progressive cross attention network (ProCANet), a deep learning model that progressively applies both self- and cross-attention mechanisms to multispectral features, generating optimal feature combinations for flood segmentation. The proposed model was compared with state-of-the-art approaches using Sen1Floods11 dataset and our bespoke flood data generated for the Citarum River basin, Indonesia. Our model demonstrated superior performance with the highest Intersection over Union (IoU) score of 0.815. Our results in this study, coupled with the ablation assessment comparing scenarios with and without attention across various modalities, opens a promising path for enhancing the accuracy of flood analysis using remote sensing technology.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Progressive Cross Attention Network for Flood Segmentation using Multispectral Satellite Imagery
Feliren, Vicky
Khikmah, Fithrothul
Bhaswara, Irfan Dwiki
Nasution, Bahrul I.
Lechner, Alex M.
Saputra, Muhamad Risqi U.
Computer Vision and Pattern Recognition
Machine Learning
86A04, 68T45
I.4.8; I.2.10
In recent years, the integration of deep learning techniques with remote sensing technology has revolutionized the way natural hazards, such as floods, are monitored and managed. However, existing methods for flood segmentation using remote sensing data often overlook the utility of correlative features among multispectral satellite information. In this study, we introduce a progressive cross attention network (ProCANet), a deep learning model that progressively applies both self- and cross-attention mechanisms to multispectral features, generating optimal feature combinations for flood segmentation. The proposed model was compared with state-of-the-art approaches using Sen1Floods11 dataset and our bespoke flood data generated for the Citarum River basin, Indonesia. Our model demonstrated superior performance with the highest Intersection over Union (IoU) score of 0.815. Our results in this study, coupled with the ablation assessment comparing scenarios with and without attention across various modalities, opens a promising path for enhancing the accuracy of flood analysis using remote sensing technology.
title Progressive Cross Attention Network for Flood Segmentation using Multispectral Satellite Imagery
topic Computer Vision and Pattern Recognition
Machine Learning
86A04, 68T45
I.4.8; I.2.10
url https://arxiv.org/abs/2501.11923