Multi-level Feature Attention Fusion Network for Water Extraction from Multi-source SAR Images
-
Abstract:
Objective: At present, water extraction from single frequency-band SAR images has achieved great success. However, due to the large differences in the characteristics of water bodies and other surface targets in SAR images with different frequency-bands, the deep learning network designed for single frequency-band has poor extraction accuracy when applied to SAR images with different frequency bands. So, how to achieve excellent extraction performance for water automatically from multi-source SAR images is still a challenge. Methods: This paper proposes a new network framework, namely Multi-level Feature Attention Fusion Network (MFAFNet). The network consists of Encoder and Decoder. The Encoder utilizes ResNet-101 to generate four-level features with different resolutions, which are then processed in parallel by the intermediate level feature fusion module (IFFM) and ECASPP module proposed in this paper, and the intermediate and high-level features are output after deep fusion; The AMM attention mechanism is introduced into Decoder to distribute the weight of low-level features, then which are further fused with the high-level features from the Encoder to obtain the water extraction results. Results: Experiments are carried out on SAR images with different frequency bands and resolutions (Sentinel-1, TerraSAR and Gaofen-3), and three good networks have been compared. The results show that the MFAFNet extraction effect is obviously better than other networks, with an average pixel accuracy of 0.87 and an average IoU of 0.80. Conclusion: The water body extraction from multi-band and multi-resolution SAR images is achieved, which promotes the practical application value of deep learning network in water body detection.
-
Keywords:
- Synthetic Aperture Radar /
- Water extraction /
- Deep learning /
- Feature fusion /
- Attention mechanism
-
-
[1] Martinis S, Groth S, Wieland M, et al. Towards a global seasonal and permanent reference water product from Sentinel-1/2 data for improved flood mapping[J]. Remote Sensing of Environment, 2022, 278:113077.
[2] Chen Lifu, Zhang Peng, Xing Jin, et al. A Multiscale Deep Neural Network for Water Detection from SAR Images in the Mountainous Areas[J]. Remote Sensing, 2020, 12(19):3205.
[3] Zhang Peng, Chen Lifu, Xing Jin, et al. Water and shadow extraction in SAR image based on a new deep learning network[J]. Sensors, 2019, 19(6):3576.
[4] Xie Cong, Huang Xin, Zeng Wenxian, et al. A novel water index for urban high-resolution eight-band WorldView-2 imagery[J]. International journal of digital earth, 2016, 9(10):925-941.
[5] Yao F, Wang C, Dong D, et al. High-resolution mapping of urban surface water using ZY-3 multi-spectral imagery[J]. Remote Sensing, 2015, 7(9):12336-12355.
[6] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[7] Li Ziyao, Wang Rui, Zhang Wen, et al. Multiscale features supported DeepLabV3+ optimization scheme for accurate water semantic segmentation[J]. IEEE Access, 2019, 7:155787-155804.
[8] Duan Lunhao, Hu Xiangyun. Multiscale refinement network for water-body segmentation in high-resolution satellite imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 17(4):686-690.
[9] Li Y, Dang B, Zhang Y, et al. Water body classification from high-resolution optical remote sensing imagery:Achievements and perspectives[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 187:306-327.
[10] Chu Zhengquan, Tian Tian, Feng Ruyi, et al. Sealand segmentation with Res-UNet and fully connected CRF[C].IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2019:3840-3843.
[11] Qin Xingli, Yang Jie, Li Pingxiang, et al.Water Body Extraction from Multi-temporal Polarimetric SAR Images Based on Transfer Learning[J]. Geomatics and Information Science of Wuhan University, 2022, 47(7):1093-1102.(覃星力,杨杰,李平湘,等.迁移学习用于多时相极化SAR影像的水体提取[J].武汉大学学报(信息科学版), 2022, 47(7):1093-1102.) [12] Sui Haigang, Chen Guang, Hu Chuanwen, et al. Integrated Segmentation, Registration and Extraction Method for Water-Body Using Optical Remote Sensing Images and GIS Data[J]. Geomatics and Information Science of Wuhan University, 2016, 41(9):1145-1150.(眭海刚,陈光,胡传文,等.光学遥感影像与GIS数据一体化的水体分割、配准与提取方法[J].武汉大学学报(信息科学版), 2016, 41(9):1145-1150.) [13] He Kaiming, Zhang Xiangyu, Ren Shaoping, et al. Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016:770-778.
[14] Wang Qilong, Wu Banggu, Zhu, Pengfei, et al. ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020.
[15] Cai Xingmin, Chen Lifu, Xing Jin, et al. Automatic extraction of layover from InSAR imagery based on multilayer feature fusion attention mechanism[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19:1-5.
[16] Chen Lifu, Luo Ru, Xing Jin, et al. Geospatial transformer is what you need for aircraft detection in SAR Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-15.
[17] Luo Ru, Chen Lifu, Xing Jin, et al. A Fast Aircraft Detection Method for SAR Images Based on Efficient Bidirectional Path Aggregated Attention Network[J]. Remote Sensing, 2021, 13:2940.
[18] Qin Jie, Wu Jie, Xiao Xuefeng, et al. Activation modulation and recalibration scheme for weakly supervised semantic segmentation[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(2):2117-2125.
[19] Chen L, Zhu Y, Papandreou G, et al. Encoderdecoder with atrous separable convolution for semantic image segmentation[C]. Proceedings of the European conference on computer vision (ECCV), 2018:801-818.
[20] Xie Enze, Wang Wenhai, Yu Zhiding, et al. SegFormer:Simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems, 2021, 34:12077-12090.
计量
- 文章访问数: 461
- HTML全文浏览量: 41
- PDF下载量: 75
下载:
