DS Net: A Dual-Coded Segmentation Network Leveraging Large Model Prior Knowledge for Intelligent Landslide Extraction.
Saved in:
| Title: | DS Net: A Dual-Coded Segmentation Network Leveraging Large Model Prior Knowledge for Intelligent Landslide Extraction. |
|---|---|
| Authors: | Wang, Xiao1,2,3 (AUTHOR), Zhong, Dongsheng2,3 (AUTHOR), Liu, Chenghao3 (AUTHOR), Song, Xiaochuan4 (AUTHOR), Xu, Luting1,2 (AUTHOR), Deng, Yue2 (AUTHOR), Li, Shaoda1,3 (AUTHOR) lisd@cdut.edu.cn |
| Source: | Remote Sensing. Jun2025, Vol. 17 Issue 11, p1912. 24p. |
| Subjects: | Remote sensing, Prior learning, Landslides, Disasters |
| Abstract: | Landslides are characterized by their suddenness and destructive power, making rapid and accurate identification crucial for emergency rescue and disaster assessment in affected areas. To address the challenges of limited landslide samples and data complexity, a landslide identification sample library was constructed using high-resolution remote sensing imagery combined with field validation. An innovative Dual-Coded Segmentation Network (DS Net), which realizes dynamic alignment and deep fusion of local details and global context, image features and domain knowledge through the multi-attention mechanism of Prior Knowledge Integration (PKI) module and Cross-Feature Aggregation (CFA) module, significantly improves the landslide detection accuracy and reliability. To objectively evaluate the performance of the DS Net model, four efficient semantic segmentation models—SegFormer, SegNeXt, FeedFormer, and U-MixFormer—were selected for comparison. The results demonstrate that DS Net achieves superior performance (overall accuracy = 0.926, precision = 0.884, recall = 0.879, and F1-score = 0.882), with metrics that are 3.5–7.1% higher than the other models. These findings confirm that DS Net effectively improves the accuracy and efficiency of landslide identification, providing a critical scientific basis for landslide prevention and mitigation. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 185869172 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: DS Net: A Dual-Coded Segmentation Network Leveraging Large Model Prior Knowledge for Intelligent Landslide Extraction. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wang%2C+Xiao%22">Wang, Xiao</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhong%2C+Dongsheng%22">Zhong, Dongsheng</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Chenghao%22">Liu, Chenghao</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Song%2C+Xiaochuan%22">Song, Xiaochuan</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Luting%22">Xu, Luting</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Deng%2C+Yue%22">Deng, Yue</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Shaoda%22">Li, Shaoda</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<i> lisd@cdut.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jun2025, Vol. 17 Issue 11, p1912. 24p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Prior+learning%22">Prior learning</searchLink><br /><searchLink fieldCode="DE" term="%22Landslides%22">Landslides</searchLink><br /><searchLink fieldCode="DE" term="%22Disasters%22">Disasters</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Landslides are characterized by their suddenness and destructive power, making rapid and accurate identification crucial for emergency rescue and disaster assessment in affected areas. To address the challenges of limited landslide samples and data complexity, a landslide identification sample library was constructed using high-resolution remote sensing imagery combined with field validation. An innovative Dual-Coded Segmentation Network (DS Net), which realizes dynamic alignment and deep fusion of local details and global context, image features and domain knowledge through the multi-attention mechanism of Prior Knowledge Integration (PKI) module and Cross-Feature Aggregation (CFA) module, significantly improves the landslide detection accuracy and reliability. To objectively evaluate the performance of the DS Net model, four efficient semantic segmentation models—SegFormer, SegNeXt, FeedFormer, and U-MixFormer—were selected for comparison. The results demonstrate that DS Net achieves superior performance (overall accuracy = 0.926, precision = 0.884, recall = 0.879, and F1-score = 0.882), with metrics that are 3.5–7.1% higher than the other models. These findings confirm that DS Net effectively improves the accuracy and efficiency of landslide identification, providing a critical scientific basis for landslide prevention and mitigation. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=185869172 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs17111912 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 24 StartPage: 1912 Subjects: – SubjectFull: Remote sensing Type: general – SubjectFull: Prior learning Type: general – SubjectFull: Landslides Type: general – SubjectFull: Disasters Type: general Titles: – TitleFull: DS Net: A Dual-Coded Segmentation Network Leveraging Large Model Prior Knowledge for Intelligent Landslide Extraction. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wang, Xiao – PersonEntity: Name: NameFull: Zhong, Dongsheng – PersonEntity: Name: NameFull: Liu, Chenghao – PersonEntity: Name: NameFull: Song, Xiaochuan – PersonEntity: Name: NameFull: Xu, Luting – PersonEntity: Name: NameFull: Deng, Yue – PersonEntity: Name: NameFull: Li, Shaoda IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 17 – Type: issue Value: 11 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
