An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images

As climate change intensifies, extreme weather events like floods are occurring with increasing frequency. While data-driven deep learning methods are effective for extracting flood disaster information, their efficiency is constrained by the scarcity of postdisaster samples, the high cost of annota...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingfei Shi, Kun Yang, Yunfang Chen, Gong Chen
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/10753337/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128609983463424
author Lingfei Shi
Kun Yang
Yunfang Chen
Gong Chen
author_facet Lingfei Shi
Kun Yang
Yunfang Chen
Gong Chen
author_sort Lingfei Shi
collection DOAJ
description As climate change intensifies, extreme weather events like floods are occurring with increasing frequency. While data-driven deep learning methods are effective for extracting flood disaster information, their efficiency is constrained by the scarcity of postdisaster samples, the high cost of annotations, and the models’ strong dependence on both the quantity and quality of data. This study introduces an interactive semantic segmentation model based on multisource UAV flood images, incorporating four types of prompts. By embedding expert knowledge into the prompt design, the model reduces annotation costs and enhances generalization capabilities. First, a prompt encoder is developed to map different types of prompt information into a three-channel space using convolutional techniques, thereby reducing sample labeling costs. Moreover, an image encoder that integrates Mamba and convolution is developed to effectively extract global spatial and channel features from flood images while minimizing computational load. Finally, a spatial and channel attention module with residual connections is introduced to enable multiscale fusion and filtering of prompt information and image features across both spatial and channel dimensions, improving the utilization of prompt information. To validate the model's performance, we conduct experiments using UAV flood imagery collected from diverse regions, backgrounds, and angles. The results demonstrate that, under consistent prompt conditions, our model extracts flood areas more efficiently, reducing misclassification and omission errors. Compared with the next best benchmark model, the intersection over union for the flood category improves by at least 3.75%.
format Article
id doaj-art-65cf23df1b7b4cf0952d4a4416a5a37e
institution Kabale University
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-65cf23df1b7b4cf0952d4a4416a5a37e2024-12-11T00:00:41ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-011893594810.1109/JSTARS.2024.349886510753337An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV ImagesLingfei Shi0https://orcid.org/0009-0009-5807-8365Kun Yang1https://orcid.org/0009-0002-6845-6381Yunfang Chen2Gong Chen3Faculty of Geography, Yunnan Normal University, Kunming, ChinaFaculty of Geography, Yunnan Normal University, Kunming, ChinaFaculty of Geography, Yunnan Normal University, Kunming, ChinaFaculty of Geography, Yunnan Normal University, Kunming, ChinaAs climate change intensifies, extreme weather events like floods are occurring with increasing frequency. While data-driven deep learning methods are effective for extracting flood disaster information, their efficiency is constrained by the scarcity of postdisaster samples, the high cost of annotations, and the models’ strong dependence on both the quantity and quality of data. This study introduces an interactive semantic segmentation model based on multisource UAV flood images, incorporating four types of prompts. By embedding expert knowledge into the prompt design, the model reduces annotation costs and enhances generalization capabilities. First, a prompt encoder is developed to map different types of prompt information into a three-channel space using convolutional techniques, thereby reducing sample labeling costs. Moreover, an image encoder that integrates Mamba and convolution is developed to effectively extract global spatial and channel features from flood images while minimizing computational load. Finally, a spatial and channel attention module with residual connections is introduced to enable multiscale fusion and filtering of prompt information and image features across both spatial and channel dimensions, improving the utilization of prompt information. To validate the model's performance, we conduct experiments using UAV flood imagery collected from diverse regions, backgrounds, and angles. The results demonstrate that, under consistent prompt conditions, our model extracts flood areas more efficiently, reducing misclassification and omission errors. Compared with the next best benchmark model, the intersection over union for the flood category improves by at least 3.75%.https://ieeexplore.ieee.org/document/10753337/Flood detectionprompt learningsemantic segmentationUAV
spellingShingle Lingfei Shi
Kun Yang
Yunfang Chen
Gong Chen
An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Flood detection
prompt learning
semantic segmentation
UAV
title An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images
title_full An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images
title_fullStr An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images
title_full_unstemmed An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images
title_short An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images
title_sort interactive prompt based network for urban floods area segmentation using uav images
topic Flood detection
prompt learning
semantic segmentation
UAV
url https://ieeexplore.ieee.org/document/10753337/
work_keys_str_mv AT lingfeishi aninteractivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages
AT kunyang aninteractivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages
AT yunfangchen aninteractivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages
AT gongchen aninteractivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages
AT lingfeishi interactivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages
AT kunyang interactivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages
AT yunfangchen interactivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages
AT gongchen interactivepromptbasednetworkforurbanfloodsareasegmentationusinguavimages