2023
DOI: 10.3390/rs15153714
|View full text |Cite
|
Sign up to set email alerts
|

Semantic Segmentation of China’s Coastal Wetlands Based on Sentinel-2 and Segformer

Abstract: Concerning the ever-changing wetland environment, the efficient extraction of wetland information holds great significance for the research and management of wetland ecosystems. China’s vast coastal wetlands possess rich and diverse geographical features. This study employs the SegFormer model and Sentinel-2 data to conduct a wetland classification study for coastal wetlands in Yancheng, Jiangsu, China. After preprocessing the Sentinel data, nine classification objects (construction land, Spartina alterniflora… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
4
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 50 publications
0
4
0
Order By: Relevance
“…Vision transformers like Segformer, Segmenter, UperNet-Swin transformer, and dense prediction transformer have been evaluated, with Segformer demonstrating superior segmentation results on UAVbased and multiscale testing datasets [42,43]. Lin et al [35] utilized the Segformer model with Sentinel-2 data for wetland classification in Yancheng, China, achieving high accuracy. In our study, the Segformer model demonstrated recognition accuracy exceeding 90% (Table 2).…”
Section: The Identification Methods Of Benggangmentioning
confidence: 99%
See 1 more Smart Citation
“…Vision transformers like Segformer, Segmenter, UperNet-Swin transformer, and dense prediction transformer have been evaluated, with Segformer demonstrating superior segmentation results on UAVbased and multiscale testing datasets [42,43]. Lin et al [35] utilized the Segformer model with Sentinel-2 data for wetland classification in Yancheng, China, achieving high accuracy. In our study, the Segformer model demonstrated recognition accuracy exceeding 90% (Table 2).…”
Section: The Identification Methods Of Benggangmentioning
confidence: 99%
“…(5) Accuracy Assessment: The accuracy of the benggang extraction results was assessed using established metrics, including accuracy (Acc), average accuracy (mAcc), (5) Accuracy Assessment: The accuracy of the benggang extraction results was assessed using established metrics, including accuracy (Acc), average accuracy (mAcc), Intersection over Union (IoU), and mean Intersection over Union (mIoU) [35]. These metrics are commonly employed in the evaluation of machine-learning models, particularly for image-segmentation tasks, providing a comprehensive assessment of the model's performance [36].…”
Section: (I) Benggang Identificationmentioning
confidence: 99%
“…Traditional wetland extraction methods mainly use manual visual interpretation techniques [21]. Traditional classification methods are often hindered by factors like image resolution, noise, and occlusion, making accurate recognition and classification challenging.…”
Section: Introductionmentioning
confidence: 99%
“…Their invaluable functions range from conserving biodiversity and supporting global hydrological cycles to mitigating climate change, highlighting their indispensable contribution to environmental balance. The rapid increase in global urbanization exerts significant stress on these ecosystems, emphasizing the urgency to adopt effective conservation measures [2]. The accurate identification, classification, and mapping of these areas are paramount, accentuating the importance of high-resolution satellite imagery for wetland segmentation.…”
Section: Introductionmentioning
confidence: 99%