SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling
Extracting water information from remote-sensing images is of great research significance for applications such as water resource protection and flood monitoring. Current water extraction methods aggregated richer multi-level features to enhance the output results. In fact, there is a difference in...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/21/3959 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173193836953600 |
|---|---|
| author | Xuejun Cheng Kuikui Han Jian Xu Guozhong Li Xiao Xiao Wengang Zhao Xianjun Gao |
| author_facet | Xuejun Cheng Kuikui Han Jian Xu Guozhong Li Xiao Xiao Wengang Zhao Xianjun Gao |
| author_sort | Xuejun Cheng |
| collection | DOAJ |
| description | Extracting water information from remote-sensing images is of great research significance for applications such as water resource protection and flood monitoring. Current water extraction methods aggregated richer multi-level features to enhance the output results. In fact, there is a difference in the requirements for the water body and the water boundary. Indiscriminate multi-feature fusion can lead to perturbation and competition of information between these two types of features during the optimization. Consequently, models cannot accurately locate the internal vacancies within the water body with the external boundary. Therefore, this paper proposes a water feature extraction network with spatial partitioning and feature decoupling. To ensure that the water features are extracted with deep semantic features and stable spatial information before decoupling, we first design a chunked multi-scale feature aggregation module (CMFAM) to construct a context path for obtaining deep semantic information. Then, an information interaction module (IIM) is designed to exchange information between two spatial paths with two fixed resolution intervals and the two paths through. During decoding, a feature decoupling module (FDM) is developed to utilize internal flow prediction to acquire the main body features, and erasing techniques are employed to obtain boundary features. Therefore, the deep features of the water body and the detailed boundary information are supplemented, strengthening the decoupled body and boundary features. Furthermore, the integrated expansion recoupling module (IERM) module is designed for the recoupling stage. The IERM expands the water body and boundary features using expansion and adaptively compensates the transition region between the water body and boundary through information guidance. Finally, multi-level constraints are combined to realize the supervision of the decoupled features. Thus, the water body and boundaries can be extracted more accurately. A comparative validation analysis is conducted on the public datasets, including the gaofen image dataset (GID) and the gaofen2020 challenge dataset (GF2020). By comparing with seven SOTAs, the results show that the proposed method achieves the best results, with IOUs of 91.22 and 78.93, especially in the localization of water bodies and boundaries. By applying the proposed method in different scenarios, the results show the stable capability of the proposed method for extracting water with various shapes and areas. |
| format | Article |
| id | doaj-art-c0cb3689e339410a8ad946ee0c60674f |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-c0cb3689e339410a8ad946ee0c60674f2024-11-08T14:40:19ZengMDPI AGRemote Sensing2072-42922024-10-011621395910.3390/rs16213959SPFDNet: Water Extraction Method Based on Spatial Partition and Feature DecouplingXuejun Cheng0Kuikui Han1Jian Xu2Guozhong Li3Xiao Xiao4Wengang Zhao5Xianjun Gao6Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaChangjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, ChinaChangjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, ChinaChangjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, ChinaHunan Institute of Water Resources and Hydropower Research, Changsha 410007, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaExtracting water information from remote-sensing images is of great research significance for applications such as water resource protection and flood monitoring. Current water extraction methods aggregated richer multi-level features to enhance the output results. In fact, there is a difference in the requirements for the water body and the water boundary. Indiscriminate multi-feature fusion can lead to perturbation and competition of information between these two types of features during the optimization. Consequently, models cannot accurately locate the internal vacancies within the water body with the external boundary. Therefore, this paper proposes a water feature extraction network with spatial partitioning and feature decoupling. To ensure that the water features are extracted with deep semantic features and stable spatial information before decoupling, we first design a chunked multi-scale feature aggregation module (CMFAM) to construct a context path for obtaining deep semantic information. Then, an information interaction module (IIM) is designed to exchange information between two spatial paths with two fixed resolution intervals and the two paths through. During decoding, a feature decoupling module (FDM) is developed to utilize internal flow prediction to acquire the main body features, and erasing techniques are employed to obtain boundary features. Therefore, the deep features of the water body and the detailed boundary information are supplemented, strengthening the decoupled body and boundary features. Furthermore, the integrated expansion recoupling module (IERM) module is designed for the recoupling stage. The IERM expands the water body and boundary features using expansion and adaptively compensates the transition region between the water body and boundary through information guidance. Finally, multi-level constraints are combined to realize the supervision of the decoupled features. Thus, the water body and boundaries can be extracted more accurately. A comparative validation analysis is conducted on the public datasets, including the gaofen image dataset (GID) and the gaofen2020 challenge dataset (GF2020). By comparing with seven SOTAs, the results show that the proposed method achieves the best results, with IOUs of 91.22 and 78.93, especially in the localization of water bodies and boundaries. By applying the proposed method in different scenarios, the results show the stable capability of the proposed method for extracting water with various shapes and areas.https://www.mdpi.com/2072-4292/16/21/3959water extractionsemantic segmentationfeature decouplingmulti-scale |
| spellingShingle | Xuejun Cheng Kuikui Han Jian Xu Guozhong Li Xiao Xiao Wengang Zhao Xianjun Gao SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling Remote Sensing water extraction semantic segmentation feature decoupling multi-scale |
| title | SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling |
| title_full | SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling |
| title_fullStr | SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling |
| title_full_unstemmed | SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling |
| title_short | SPFDNet: Water Extraction Method Based on Spatial Partition and Feature Decoupling |
| title_sort | spfdnet water extraction method based on spatial partition and feature decoupling |
| topic | water extraction semantic segmentation feature decoupling multi-scale |
| url | https://www.mdpi.com/2072-4292/16/21/3959 |
| work_keys_str_mv | AT xuejuncheng spfdnetwaterextractionmethodbasedonspatialpartitionandfeaturedecoupling AT kuikuihan spfdnetwaterextractionmethodbasedonspatialpartitionandfeaturedecoupling AT jianxu spfdnetwaterextractionmethodbasedonspatialpartitionandfeaturedecoupling AT guozhongli spfdnetwaterextractionmethodbasedonspatialpartitionandfeaturedecoupling AT xiaoxiao spfdnetwaterextractionmethodbasedonspatialpartitionandfeaturedecoupling AT wengangzhao spfdnetwaterextractionmethodbasedonspatialpartitionandfeaturedecoupling AT xianjungao spfdnetwaterextractionmethodbasedonspatialpartitionandfeaturedecoupling |