Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups
Forests are the most important carbon reservoirs on land, and forest carbon sinks can effectively reduce atmospheric CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2&l...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/15/3875 |
| _version_ | 1797586008878874624 |
|---|---|
| author | Zhenyu Yu Jinnian Wang Xiankun Yang Juan Ma |
| author_facet | Zhenyu Yu Jinnian Wang Xiankun Yang Juan Ma |
| author_sort | Zhenyu Yu |
| collection | DOAJ |
| description | Forests are the most important carbon reservoirs on land, and forest carbon sinks can effectively reduce atmospheric CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula> concentrations and mitigate climate change. In recent years, various satellites have been launched that provide opportunities for identifying forest types with low cost and high time efficiency. Using multi-temporal remote sensing images and combining them with vegetation indices takes into account the vegetation growth pattern and substantially improves the identification accuracy, but it has high requirements for imaging, such as registration, multiple times, etc. Sometimes, it is difficult to satisfy, the plateau area is severely limited by the influence of clouds and rain, and Gaofen (GF) data require more control points for orthophoto correction. The study area was chosen to be Huize County, situated in Qujing City of Yunnan Province, China. The analysis was using the GF and Landsat images. According to deep learning and remote sensing image feature extraction methods, the semantic segmentation method of F-Pix2Pix was proposed, and the domain adaptation method according to transfer learning effectively solved the class imbalance in needleleaf/broadleaf forest identification. The results showed that (1) this method had the best performance and a higher accuracy than the existing products, 21.48% in non-forest/forest and 29.44% in needleleaf/broadleaf forest for MIoU improvement. (2) Applying transfer learning domain adaptation to semantic segmentation showed significant benefits, and this approach utilized satellite images of different resolutions to solve the class imbalance problem. (3) It can be used for long-term monitoring of multiple images and has strong generalization. The identification of needleleaf and broadleaf forests combined with the actual geographical characteristics of the forest provides a foundation for the accurate estimation of regional carbon sources/sinks. |
| first_indexed | 2024-03-11T00:17:14Z |
| format | Article |
| id | doaj.art-2fd9bb5c9c6e4ec78791442ce495bf74 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T00:17:14Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2fd9bb5c9c6e4ec78791442ce495bf742023-11-18T23:32:02ZengMDPI AGRemote Sensing2072-42922023-08-011515387510.3390/rs15153875Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type GroupsZhenyu Yu0Jinnian Wang1Xiankun Yang2Juan Ma3School of Geography and Remote Sensing, Guangzhou University, Guangzhou 510006, ChinaSchool of Geography and Remote Sensing, Guangzhou University, Guangzhou 510006, ChinaSchool of Geography and Remote Sensing, Guangzhou University, Guangzhou 510006, ChinaForestry and Grassland Bureau of Huize County, Qujing 654299, ChinaForests are the most important carbon reservoirs on land, and forest carbon sinks can effectively reduce atmospheric CO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula> concentrations and mitigate climate change. In recent years, various satellites have been launched that provide opportunities for identifying forest types with low cost and high time efficiency. Using multi-temporal remote sensing images and combining them with vegetation indices takes into account the vegetation growth pattern and substantially improves the identification accuracy, but it has high requirements for imaging, such as registration, multiple times, etc. Sometimes, it is difficult to satisfy, the plateau area is severely limited by the influence of clouds and rain, and Gaofen (GF) data require more control points for orthophoto correction. The study area was chosen to be Huize County, situated in Qujing City of Yunnan Province, China. The analysis was using the GF and Landsat images. According to deep learning and remote sensing image feature extraction methods, the semantic segmentation method of F-Pix2Pix was proposed, and the domain adaptation method according to transfer learning effectively solved the class imbalance in needleleaf/broadleaf forest identification. The results showed that (1) this method had the best performance and a higher accuracy than the existing products, 21.48% in non-forest/forest and 29.44% in needleleaf/broadleaf forest for MIoU improvement. (2) Applying transfer learning domain adaptation to semantic segmentation showed significant benefits, and this approach utilized satellite images of different resolutions to solve the class imbalance problem. (3) It can be used for long-term monitoring of multiple images and has strong generalization. The identification of needleleaf and broadleaf forests combined with the actual geographical characteristics of the forest provides a foundation for the accurate estimation of regional carbon sources/sinks.https://www.mdpi.com/2072-4292/15/15/3875forest identificationsuperpixelsemantic segmentationclass imbalanceneedleleaf and broadleaf forest |
| spellingShingle | Zhenyu Yu Jinnian Wang Xiankun Yang Juan Ma Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups Remote Sensing forest identification superpixel semantic segmentation class imbalance needleleaf and broadleaf forest |
| title | Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups |
| title_full | Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups |
| title_fullStr | Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups |
| title_full_unstemmed | Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups |
| title_short | Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups |
| title_sort | superpixel based style transfer method for single temporal remote sensing image identification in forest type groups |
| topic | forest identification superpixel semantic segmentation class imbalance needleleaf and broadleaf forest |
| url | https://www.mdpi.com/2072-4292/15/15/3875 |
| work_keys_str_mv | AT zhenyuyu superpixelbasedstyletransfermethodforsingletemporalremotesensingimageidentificationinforesttypegroups AT jinnianwang superpixelbasedstyletransfermethodforsingletemporalremotesensingimageidentificationinforesttypegroups AT xiankunyang superpixelbasedstyletransfermethodforsingletemporalremotesensingimageidentificationinforesttypegroups AT juanma superpixelbasedstyletransfermethodforsingletemporalremotesensingimageidentificationinforesttypegroups |