Water Extraction in PolSAR Image Based on Superpixel and Graph Convolutional Network
Source abstract
Abstract
The timely detection and mapping of surface water bodies from Polarimetric Synthetic Aperture Radar (PolSAR) images are of great significance for emergency management and post-disaster restoration tasks. Though various methods have been proposed in previous years, there are still some inherent flaws. Thus, this paper proposes a new surface water extraction method based on superpixels and Graph Convolutional Networks (GCN). First, the PolSAR images are segmented to generate superpixels as the basic unit of classification, and the graph structure data are established according to their connection to superpixels. Then, the features of each superpixel are extracted. Finally, a GCN is used to classify each superpixel unit using node features and their relationships. This study conducted experiments on a sudden flooding event due to heavy rain and a lake in the city. Detailed verification was carried out. Compared to traditional methods, the recall was improved by 3% while maintaining almost 100% accuracy in complex flood areas. The results show that the proposed method of surface water extraction from PolSAR images has great advantages, acquiring higher accuracy and better boundary adherence in cases of fewer samples. This paper also illustrates the advantage of using GCN to mine the contextual information of classification objects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Flood Risk Assessment and Management · Remote-Sensing Image Classification · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Research Center of Big Data Technology, Nanhu Laboratory, Jiaxing 314002, China
Advanced Institute of Big Data, Beijing 100093, China
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
Laboratory of Target Microwave Properties, Deqing Academy of Satellite Applications, Huzhou 313200, China
College of Nature Resources and Environment, South China Agricultural University, Guangzhou 510642, China
School of Civil Engineering and Architecture, Jiaxing Nanhu University, Jiaxing 314001, China
Funding
Open Research Fund of Laboratory of Target Microwave Properties · the nonprofit research project of Jiaxing City
References (42)
Show source-provided references
1. An Urban Water Extraction Method Combining Deep Learning and Google Earth Engine10.1109/JSTARS.2020.2971783 ↗
2. Ulloa, N.I., Chiang, S.-H., and Yun, S.-H. (2020). Flood Proxy Mapping with Normalized Difference Sigma-Naught Index and Shannon’s Entropy. Remote Sens., 12.10.3390/rs12091384 ↗
3. Satellite imaging reveals increased proportion of population exposed to floods10.1038/s41586-021-03695-w ↗
4. Declining vulnerability to river floods and the global benefits of adaptation10.1073/pnas.1414439112 ↗
5. Satellite Image Analysis for Disaster and Crisis-Management Support10.1109/TGRS.2007.895830 ↗
6. The Utility of Spaceborne Radar to Render Flood Inundation Maps Based on Multialgorithm Ensembles10.1109/TGRS.2009.2017937 ↗
7. River Planform Extraction From High-Resolution SAR Images via Generalized Gamma Distribution Superpixel Classification10.1109/TGRS.2020.3011209 ↗
8. Marghany, M. (2021). Nonlinear Ocean Dynamics: Synthetic Aperture Radar, Elsevier.10.1016/B978-0-12-821796-2.00013-6 ↗
9. Marghany, M. (2020). Synthetic Aperture Radar Imaging Mechanism for Oil Spills, Gulf Professional Publishing.10.1016/B978-0-12-818111-9.00001-X ↗
10. Ndikumana, E., Minh, D.H.T., Baghdadi, N., Courault, D., and Hossard, L. (2018). Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France. Remote Sens., 10.10.3390/rs10081217 ↗
11. Hoekstra, M., Jiang, M., Clausi, D.A., and Duguay, C. (2020). Lake Ice-Water Classification of RADARSAT-2 Images by Integrating IRGS Segmentation with Pixel-Based Random Forest Labeling. Remote Sens., 12.10.3390/rs12091425 ↗
12. Zoka, M., Psomiadis, E., and Dercas, N. (2018). The Complementary Use of Optical and SAR Data in Monitoring Flood Events and Their Effects. EWaS3 2018, 2.10.3390/proceedings2110644 ↗
13. Envisat multi-polarized ASAR data for flood mapping10.1080/01431160500486724 ↗
14. Integration of remote sensing data and GIS for accurate mapping of flooded areas10.1080/01431160010014729 ↗
15. Progress in operational flood mapping using satellite synthetic aperture radar (SAR) and airborne light detection and ranging (LiDAR) data10.1177/0309133316633570 ↗
16. Improved ACM Algorithm for Poyang Lake Monitoring
17. Bao, L., Lv, X., and Yao, J. (2021). Water Extraction in SAR Images Using Features Analysis and Dual-Threshold Graph Cut Model. Remote Sens., 13.10.3390/rs13173465 ↗
18. Zhu, W., Dai, Z., Gu, H., and Zhu, X. (2021). Water Extraction Method Based on Multi-Texture Feature Fusion of Synthetic Aperture Radar Images. Sensors, 21.10.3390/s21144945 ↗
19. Waterline Mapping and Change Detection of Tangjiashan Dammed Lake After Wenchuan Earthquake From Multitemporal High-Resolution Airborne SAR Imagery10.1109/JSTARS.2014.2345417 ↗
20. Xie, L., Zhang, H., and Wang, C. (2015, January 3–5). Water-body types classification using Radarsat-2 fully polarimetric SAR data. Proceedings of the 2015 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES), Bali, Indonesia.10.1109/ICARES.2015.7429816 ↗
21. Lv, W., Yu, Q., and Yu, W. (2010, January 24–28). Water extraction in SAR images using GLCM and Support Vector Machine. Proceedings of the IEEE 10th International Conference on Signal Processing, Beijing, China.
22. Water Area Extraction Using RADARSAT SAR Imagery Combined with Landsat Imagery and Terrain Information10.3390/s150306652 ↗
23. Huang, W., Li, H., and Lin, G. (2015, January 8–10). Classifying forest stands based on multi-scale structure features using Quickbird image. Proceedings of the 2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM), Fuzhou, China.10.1109/ICSDM.2015.7298054 ↗
24. Paul, S., and Ganju, S. (2021). Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning. arXiv.
25. A recurrent curve matching classification method integrating within-object spectral variability and between-object spatial association
26. Deep Learning Meets SAR: Concepts, Models, Pitfalls, and Perspectives10.1109/MGRS.2020.3046356 ↗
27. Hu, H., Ji, D., Gan, W., Bai, S., Wu, W., and Yan, J. (2020, January 23–28). Class-Wise Dynamic Graph Convolution for Semantic Segmentation. Proceedings of the 16th European Conference, Glasgow, UK.10.1007/978-3-030-58520-4_1 ↗
28. Liu, Q., Kampffmeyer, M., Jenssen, R., and Salberg, A.B. (2020). SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation. arXiv.10.1109/IGARSS39084.2020.9324719 ↗
29. He, C., He, B., Tu, M., Wang, Y., Qu, T., Wang, D., and Liao, M. (2020). Fully Convolutional Networks and a Manifold Graph Embedding-Based Algorithm for PolSAR Image Classification. Remote Sens., 12.10.3390/rs12091467 ↗
30. Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation10.1109/TPAMI.2021.3083269 ↗
31. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods10.1109/TPAMI.2012.120 ↗
32. Stochastic Neighbor Embedding
33. Superpixel Generating Algorithm Based on Pixel Intensity and Location Similarity for SAR Image Classification10.1109/LGRS.2013.2259214 ↗
34. SLIC Superpixel Segmentation for Polarimetric SAR Images
35. Mixture-Based Superpixel Segmentation and Classification of SAR Images10.1109/LGRS.2016.2605583 ↗
36. Efficient Texture Analysis of SAR Imagery10.1109/TGRS.2005.852768 ↗
37. Adaptive Superpixel Generation for Polarimetric SAR Images With Local Iterative Clustering and SIRV Model10.1109/TGRS.2017.2662010 ↗
38. A threshold selection method from gray-histogram10.1109/TSMC.1979.4310076 ↗
39. Hamilton, W.L., Ying, R., and Leskovec, J. (2017). Inductive Representation Learning on Large Graphs. Adv. Neural Inf. Process. Syst., 30.
40. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
41. Marghany, M. (2022). Advanced Algorithms for Mineral and Hydrocarbon Exploration Using Synthetic Aperture Radar, Elsevier.10.1016/B978-0-12-821796-2.00005-7 ↗
42. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (May, January 30). Graph Attention Networks. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.