SwinClustering: a new paradigm for landscape character assessment through visual segmentation
The research value of Landscape Character Assessment (LCA) lies in gaining a deeper understanding of the inherent attributes and interrelationships of various landscapes, thereby providing scientific basis for landscape planning, design, conservation, and sustainable utilization. The traditional LCA...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Environmental Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenvs.2025.1509113/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859154110906368 |
|---|---|
| author | Tingting Huang Tingting Huang Bo Huang Bo Huang Sha Li Haiyue Zhao Xin Yang Jianning Zhu |
| author_facet | Tingting Huang Tingting Huang Bo Huang Bo Huang Sha Li Haiyue Zhao Xin Yang Jianning Zhu |
| author_sort | Tingting Huang |
| collection | DOAJ |
| description | The research value of Landscape Character Assessment (LCA) lies in gaining a deeper understanding of the inherent attributes and interrelationships of various landscapes, thereby providing scientific basis for landscape planning, design, conservation, and sustainable utilization. The traditional LCA methods often overlook the inherent connections between various landscape attributes and geographical spatial relationships among data points, which restricts their application in sustainable multi-scale landscape element assessments. Accordingly, this paper proposes a new paradigm for LCA, SwinClustering, built upon the cutting-edge Swin Transformer architecture. This approach employs a visual segmentation method to achieve multi-scale clustering, utilizing nine key attributes of landscape elements: altitude, aspect, geology, landcover, landform, relief, slope, soil, and vegetation. By extracting semantic features through the GIS-aware Swin Transformer backbone network and leveraging the Feature Pyramid Decoder for segmentation clustering, SwinClustering offers a comprehensive analysis of landscape characteristics. Furthermore, we design a specific training strategy that enables coarseness and fineness control of the clustering results. SwinClustering is tested across three distinct scales: the national scale of China, the municipal scale of Beijing Municipality and the district scale of Wuyishan National Park. These experiments yield promising results, validating the method’s effectiveness across diverse geographic scales. Crucially, the proposed SwinClustering paradigm establishes a unified clustering framework to deeply learn the intrinsic connection between various landscape attributes and the spatial relationship between different geographic locations. Furthermore, its strong generalization capabilities enable its seamless application to LCA tasks at arbitrary scales, marking a sustainable development in the field of LCA. |
| format | Article |
| id | doaj-art-073906990911478fbd19e8e3f67289aa |
| institution | Kabale University |
| issn | 2296-665X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Environmental Science |
| spelling | doaj-art-073906990911478fbd19e8e3f67289aa2025-02-11T06:59:25ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2025-02-011310.3389/fenvs.2025.15091131509113SwinClustering: a new paradigm for landscape character assessment through visual segmentationTingting Huang0Tingting Huang1Bo Huang2Bo Huang3Sha Li4Haiyue Zhao5Xin Yang6Jianning Zhu7School of Landscape Architecture, Beijing Forestry University, Beijing, ChinaSchool of Agriculture, Policy and Development, University of Reading, Reading, United KingdomCollege of Optoelectronic Engineering, Chongqing University, Chongqing, ChinaKey Laboratory of Optoelectronic Technology and Systems of the Education Ministry of China, Chongqing University, Chongqing, ChinaSchool of Architecture and Design, China University of Mining and Technology, Xuzhou, ChinaSchool of Landscape Architecture, Beijing Forestry University, Beijing, ChinaCollege of Architecture and Art, North China University of Technology, Beijing, ChinaSchool of Landscape Architecture, Beijing Forestry University, Beijing, ChinaThe research value of Landscape Character Assessment (LCA) lies in gaining a deeper understanding of the inherent attributes and interrelationships of various landscapes, thereby providing scientific basis for landscape planning, design, conservation, and sustainable utilization. The traditional LCA methods often overlook the inherent connections between various landscape attributes and geographical spatial relationships among data points, which restricts their application in sustainable multi-scale landscape element assessments. Accordingly, this paper proposes a new paradigm for LCA, SwinClustering, built upon the cutting-edge Swin Transformer architecture. This approach employs a visual segmentation method to achieve multi-scale clustering, utilizing nine key attributes of landscape elements: altitude, aspect, geology, landcover, landform, relief, slope, soil, and vegetation. By extracting semantic features through the GIS-aware Swin Transformer backbone network and leveraging the Feature Pyramid Decoder for segmentation clustering, SwinClustering offers a comprehensive analysis of landscape characteristics. Furthermore, we design a specific training strategy that enables coarseness and fineness control of the clustering results. SwinClustering is tested across three distinct scales: the national scale of China, the municipal scale of Beijing Municipality and the district scale of Wuyishan National Park. These experiments yield promising results, validating the method’s effectiveness across diverse geographic scales. Crucially, the proposed SwinClustering paradigm establishes a unified clustering framework to deeply learn the intrinsic connection between various landscape attributes and the spatial relationship between different geographic locations. Furthermore, its strong generalization capabilities enable its seamless application to LCA tasks at arbitrary scales, marking a sustainable development in the field of LCA.https://www.frontiersin.org/articles/10.3389/fenvs.2025.1509113/fulllandscape character assessmentcharacter clusteringGIS-awareswin transformervisual segmentation |
| spellingShingle | Tingting Huang Tingting Huang Bo Huang Bo Huang Sha Li Haiyue Zhao Xin Yang Jianning Zhu SwinClustering: a new paradigm for landscape character assessment through visual segmentation Frontiers in Environmental Science landscape character assessment character clustering GIS-aware swin transformer visual segmentation |
| title | SwinClustering: a new paradigm for landscape character assessment through visual segmentation |
| title_full | SwinClustering: a new paradigm for landscape character assessment through visual segmentation |
| title_fullStr | SwinClustering: a new paradigm for landscape character assessment through visual segmentation |
| title_full_unstemmed | SwinClustering: a new paradigm for landscape character assessment through visual segmentation |
| title_short | SwinClustering: a new paradigm for landscape character assessment through visual segmentation |
| title_sort | swinclustering a new paradigm for landscape character assessment through visual segmentation |
| topic | landscape character assessment character clustering GIS-aware swin transformer visual segmentation |
| url | https://www.frontiersin.org/articles/10.3389/fenvs.2025.1509113/full |
| work_keys_str_mv | AT tingtinghuang swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation AT tingtinghuang swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation AT bohuang swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation AT bohuang swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation AT shali swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation AT haiyuezhao swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation AT xinyang swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation AT jianningzhu swinclusteringanewparadigmforlandscapecharacterassessmentthroughvisualsegmentation |