Loading…

UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery

Satellite remote sensing (RS) has been drawing considerable research interest in land-cover classification due to its low price, short revisit time, and large coverage. However, clouds pose a significant challenge, occluding the objects on satellite RS images. In addition, snow coverage mapping play...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinge Ma, Haoran Shen, Yuanxiu Cai, Tianxiang Zhang, Jinya Su, Wen-Hua Chen, Jiangyun Li
Format: Default Article
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/2134/26106358.v1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1824423478420307968
author Jinge Ma
Haoran Shen
Yuanxiu Cai
Tianxiang Zhang
Jinya Su
Wen-Hua Chen
Jiangyun Li
author_facet Jinge Ma
Haoran Shen
Yuanxiu Cai
Tianxiang Zhang
Jinya Su
Wen-Hua Chen
Jiangyun Li
author_sort Jinge Ma (745159)
collection Figshare
description Satellite remote sensing (RS) has been drawing considerable research interest in land-cover classification due to its low price, short revisit time, and large coverage. However, clouds pose a significant challenge, occluding the objects on satellite RS images. In addition, snow coverage mapping plays a vital role in studying hydrology and climatology and investigating crop disease overwintering for smart agriculture. Distinguishing snow from clouds is challenging since they share similar color and reflection characteristics. Conventional approaches with manual thresholding and machine learning algorithms (e.g., SVM and Random Forest) could not fully extract useful information, while current deep-learning methods, e.g., CNNs or Transformer models, still have limitations in fully exploiting abundant spatial/spectral information of RS images. Therefore, this work aims to develop an efficient snow and cloud classification algorithm using satellite multispectral RS images. In particular, we propose an innovative algorithm entitled UCTNet by adopting a dual-flow structure to integrate information extracted via Transformer and CNN branches. Particularly, CNN and Transformer integration Module (CTIM) is designed to maximally integrate the information extracted via two branches. Meanwhile, Final Information Fusion Module and Auxiliary Information Fusion Head are designed for better performance. The four-band satellite multispectral RS dataset for snow coverage mapping is adopted for performance evaluation. Compared with previous methods (e.g., U-Net, Swin, and CSDNet), the experimental results show that the proposed UCTNet achieves the best performance in terms of accuracy (95.72%) and mean IoU score (91.21%) while with the smallest model size (3.93 M). The confirmed efficiency of UCTNet shows great potential for dual-flow architecture on snow and cloud classification.
format Default
Article
id rr-article-26106358
institution Loughborough University
publishDate 2023
record_format Figshare
spelling rr-article-261063582023-08-27T01:00:00Z UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery Jinge Ma (745159) Haoran Shen (11286273) Yuanxiu Cai (20742696) Tianxiang Zhang (3375752) Jinya Su (1260438) Wen-Hua Chen (1251597) Jiangyun Li (11500642) Atmospheric sciences Physical geography and environmental geoscience Geomatic engineering Classical physics Multispectral imagery Satellite remote sensing Snow coverage mapping UCTNet Satellite remote sensing (RS) has been drawing considerable research interest in land-cover classification due to its low price, short revisit time, and large coverage. However, clouds pose a significant challenge, occluding the objects on satellite RS images. In addition, snow coverage mapping plays a vital role in studying hydrology and climatology and investigating crop disease overwintering for smart agriculture. Distinguishing snow from clouds is challenging since they share similar color and reflection characteristics. Conventional approaches with manual thresholding and machine learning algorithms (e.g., SVM and Random Forest) could not fully extract useful information, while current deep-learning methods, e.g., CNNs or Transformer models, still have limitations in fully exploiting abundant spatial/spectral information of RS images. Therefore, this work aims to develop an efficient snow and cloud classification algorithm using satellite multispectral RS images. In particular, we propose an innovative algorithm entitled UCTNet by adopting a dual-flow structure to integrate information extracted via Transformer and CNN branches. Particularly, CNN and Transformer integration Module (CTIM) is designed to maximally integrate the information extracted via two branches. Meanwhile, Final Information Fusion Module and Auxiliary Information Fusion Head are designed for better performance. The four-band satellite multispectral RS dataset for snow coverage mapping is adopted for performance evaluation. Compared with previous methods (e.g., U-Net, Swin, and CSDNet), the experimental results show that the proposed UCTNet achieves the best performance in terms of accuracy (95.72%) and mean IoU score (91.21%) while with the smallest model size (3.93 M). The confirmed efficiency of UCTNet shows great potential for dual-flow architecture on snow and cloud classification.<p></p> 2023-08-27T01:00:00Z Text Journal contribution 2134/26106358.v1 https://figshare.com/articles/journal_contribution/UCTNet_with_dual-flow_architecture_snow_coverage_mapping_with_Sentinel-2_satellite_Imagery/26106358 CC BY 4.0
spellingShingle Atmospheric sciences
Physical geography and environmental geoscience
Geomatic engineering
Classical physics
Multispectral imagery
Satellite remote sensing
Snow coverage mapping
UCTNet
Jinge Ma
Haoran Shen
Yuanxiu Cai
Tianxiang Zhang
Jinya Su
Wen-Hua Chen
Jiangyun Li
UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery
title UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery
title_full UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery
title_fullStr UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery
title_full_unstemmed UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery
title_short UCTNet with dual-flow architecture: snow coverage mapping with Sentinel-2 satellite Imagery
title_sort uctnet with dual-flow architecture: snow coverage mapping with sentinel-2 satellite imagery
topic Atmospheric sciences
Physical geography and environmental geoscience
Geomatic engineering
Classical physics
Multispectral imagery
Satellite remote sensing
Snow coverage mapping
UCTNet
url https://hdl.handle.net/2134/26106358.v1