EDWNet: A Novel Encoder–Decoder Architecture Network for Water Body Extraction from Optical Images

Automated water body (WB) extraction is one of the hot research topics in the field of remote sensing image processing. To address the challenges of over-extraction and incomplete extraction in complex water scenes, we propose an encoder–decoder architecture semantic segmentation network for high-pr...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Remote sensing (Basel, Switzerland) Ročník 16; číslo 22; s. 4275
Hlavní autoři: Zhang, Tianyi, Ji, Wenbo, Li, Weibin, Qin, Chenhao, Wang, Tianhao, Ren, Yi, Fang, Yuan, Han, Zhixiong, Jiao, Licheng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.11.2024
Témata:
Algorithms
Analysis
Artificial intelligence
China
Classification
Climate change
Coders
Computer vision
Dams
Deep learning
Diffusion layers
Earth resources technology satellites
EDWNet
Image enhancement
Image processing
Image segmentation
Information processing
Landsat
Modules
Neural networks
Remote sensing
River basins
Satellite imagery
Semantic segmentation
Surface water
Water bodies
water body
Weihe river basin
China
Weihe River
Yellow River
ISSN:2072-4292, 2072-4292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Automated water body (WB) extraction is one of the hot research topics in the field of remote sensing image processing. To address the challenges of over-extraction and incomplete extraction in complex water scenes, we propose an encoder–decoder architecture semantic segmentation network for high-precision extraction of WBs called EDWNet. We integrate the Cross-layer Feature Fusion (CFF) module to solve difficulties in segmentation of WB edges, utilizing the Global Attention Mechanism (GAM) module to reduce information diffusion, and combining with the Deep Attention Module (DAM) module to enhance the model’s global perception ability and refine WB features. Additionally, an auxiliary head is incorporated to optimize the model’s learning process. In addition, we analyze the feature importance of bands 2 to 7 in Landsat 8 OLI images, constructing a band combination (RGB 763) suitable for algorithm’s WB extraction. When we compare EDWNet with various other semantic segmentation networks, the results on the test dataset show that EDWNet has the highest accuracy. EDWNet is applied to accurately extract WBs in the Weihe River basin from 2013 to 2021, and we quantitatively analyzed the area changes of the WBs during this period and their causes. The results show that EDWNet is suitable for WB extraction in complex scenes and demonstrates great potential in long time-series and large-scale WB extraction.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2072-4292
2072-4292
DOI:10.3390/rs16224275