GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed images
Accurate classification of urban green spaces from high-resolution remotely sensed images is critical for ecological environment planning, construction, and utilization. However, existing deep learning networks for large-scale high-resolution remote sensing images often face limited receptive fields...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843225003565 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849335635991592960 |
|---|---|
| author | Ke Chen Yang Wang Cunrui Huang Jing Wang Sabrina L. Li Haiyan Guan Lingfei Ma |
| author_facet | Ke Chen Yang Wang Cunrui Huang Jing Wang Sabrina L. Li Haiyan Guan Lingfei Ma |
| author_sort | Ke Chen |
| collection | DOAJ |
| description | Accurate classification of urban green spaces from high-resolution remotely sensed images is critical for ecological environment planning, construction, and utilization. However, existing deep learning networks for large-scale high-resolution remote sensing images often face limited receptive fields and insufficient extraction of global information, making it challenging to achieve satisfactory performance on urban green space classification tasks. To address these issues, this paper presents a novel dual-encoder network, termed GreenNet, specifically designed for urban green space classification from high-resolution remotely sensed images. GreenNet features a unique dual-encoder structure. i.e., an inside encoder for efficiently extracting interior intra-image (i.e., local and global) features of urban green spaces from the small-sized images cropped from raw input remote sensing images, and an outside encoder for modeling long dependencies (i.e., external inter-image features) from the large-sized images cropped from raw input images. Additionally, a transformer-based outside-global–local attention block (OGLAB) is developed to fuse the intra-image and inter-image features from the dual-encoder to effectively capture inherent semantic representations of urban green spaces. Finally, to ensure classification consistency along class boundaries, a boundary loss is computed using edge-defined images, which are generated by a pre-trained Segmenting Anything Model (SAM) from the raw input image. The proposed GreenNet was evaluated on a self-built urban green space dataset, covering the whole area of Nanshan District, Shenzhen City, China, achieving an overall accuracy (OA) of 88.88 %, a mean F1-score (mF1) of 74.06 %, and a mean Intersection over Union (mIoU) of 60.77 %, respectively, demonstrating its superior performance to state-of-the-art networks on green space classification tasks. |
| format | Article |
| id | doaj-art-db09a8d1dd03443a984c8a004e4c8ae3 |
| institution | Kabale University |
| issn | 1569-8432 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-db09a8d1dd03443a984c8a004e4c8ae32025-08-20T03:45:11ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-08-0114210470910.1016/j.jag.2025.104709GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed imagesKe Chen0Yang Wang1Cunrui Huang2Jing Wang3Sabrina L. Li4Haiyan Guan5Lingfei Ma6School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaVanke School of Public Health, Tsinghua University, Beijing 100084, China; Corresponding authors.School of Geographic Sciences and Tourism, Jilin Normal University, Siping 136000, China; Corresponding authors.School of Geography, University of Nottingham, Nottingham NG7 2RD, United KingdomSchool of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Statistics and Mathematics, Central University of Finance and Economics, Beijing 102206, ChinaAccurate classification of urban green spaces from high-resolution remotely sensed images is critical for ecological environment planning, construction, and utilization. However, existing deep learning networks for large-scale high-resolution remote sensing images often face limited receptive fields and insufficient extraction of global information, making it challenging to achieve satisfactory performance on urban green space classification tasks. To address these issues, this paper presents a novel dual-encoder network, termed GreenNet, specifically designed for urban green space classification from high-resolution remotely sensed images. GreenNet features a unique dual-encoder structure. i.e., an inside encoder for efficiently extracting interior intra-image (i.e., local and global) features of urban green spaces from the small-sized images cropped from raw input remote sensing images, and an outside encoder for modeling long dependencies (i.e., external inter-image features) from the large-sized images cropped from raw input images. Additionally, a transformer-based outside-global–local attention block (OGLAB) is developed to fuse the intra-image and inter-image features from the dual-encoder to effectively capture inherent semantic representations of urban green spaces. Finally, to ensure classification consistency along class boundaries, a boundary loss is computed using edge-defined images, which are generated by a pre-trained Segmenting Anything Model (SAM) from the raw input image. The proposed GreenNet was evaluated on a self-built urban green space dataset, covering the whole area of Nanshan District, Shenzhen City, China, achieving an overall accuracy (OA) of 88.88 %, a mean F1-score (mF1) of 74.06 %, and a mean Intersection over Union (mIoU) of 60.77 %, respectively, demonstrating its superior performance to state-of-the-art networks on green space classification tasks.http://www.sciencedirect.com/science/article/pii/S1569843225003565Green space classificationHigh-resolution satellite imagesDual-encoder structureTransformerBoundary loss |
| spellingShingle | Ke Chen Yang Wang Cunrui Huang Jing Wang Sabrina L. Li Haiyan Guan Lingfei Ma GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed images International Journal of Applied Earth Observations and Geoinformation Green space classification High-resolution satellite images Dual-encoder structure Transformer Boundary loss |
| title | GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed images |
| title_full | GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed images |
| title_fullStr | GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed images |
| title_full_unstemmed | GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed images |
| title_short | GreenNet: A dual-encoder network for urban green space classification using high-resolution remotely sensed images |
| title_sort | greennet a dual encoder network for urban green space classification using high resolution remotely sensed images |
| topic | Green space classification High-resolution satellite images Dual-encoder structure Transformer Boundary loss |
| url | http://www.sciencedirect.com/science/article/pii/S1569843225003565 |
| work_keys_str_mv | AT kechen greennetadualencodernetworkforurbangreenspaceclassificationusinghighresolutionremotelysensedimages AT yangwang greennetadualencodernetworkforurbangreenspaceclassificationusinghighresolutionremotelysensedimages AT cunruihuang greennetadualencodernetworkforurbangreenspaceclassificationusinghighresolutionremotelysensedimages AT jingwang greennetadualencodernetworkforurbangreenspaceclassificationusinghighresolutionremotelysensedimages AT sabrinalli greennetadualencodernetworkforurbangreenspaceclassificationusinghighresolutionremotelysensedimages AT haiyanguan greennetadualencodernetworkforurbangreenspaceclassificationusinghighresolutionremotelysensedimages AT lingfeima greennetadualencodernetworkforurbangreenspaceclassificationusinghighresolutionremotelysensedimages |