基于TA-UNet3+的高分辨率遥感图像地表水体提取

doi:10.3778/j.issn.1002-8331.2404-0094

摘要/Abstract

摘要： 遥感图像中准确提取地表水体信息对于水资源管理、环境监测等领域至关重要。然而，由于地表覆盖的多样性、水体与周围环境的交汇、植被的复杂遮挡等因素，使得这项任务仍然面临着一系列挑战。为了提高地表水体提取精度，基于U-Net3+网络进行优化，提出了一种适用于高分辨率遥感图像的TA-UNet3+网络模型。在编码器端由深度特征到浅层逐层引入窗口注意力嵌入模块，将来自更深层特征的局部注意力逐步嵌入到较低级特征中，提高特征图的语义理解能力。引入了结合阈值注意力和深度可分离的TA-ASPP模块，有效提高了特征信息的提取效率。在解码器端修改了多尺度融合模块，采用可学习的密集上采样卷积和深度分离卷积替代原始的双线性插值与普通卷积，在保证精度的同时显著降低了计算复杂度。数据集选择了重庆市不同场景下的部分地区，实验结果表明，TA-UNet3+网络模型在精度、召回率、F1和IoU等评价指标上均优于语义分割网络，表现出更高的地表水体提取精度。

关键词: 地表水体提取, 遥感图像, TA-UNet3+, 阈值注意力, 密集上采样卷积, TA-ASPP模块, 窗口注意力

Abstract: Accurate extraction of surface water information from remote sensing images is crucial for water resources management, environmental monitoring and other fields. However, this task still faces a series of challenges due to factors such as the diversity of land cover, the intersection of water bodies and the surrounding environment, and complex occlusion of vegetation. In order to improve the accuracy of surface water extraction, a TA-UNet3+ network model suitable for high-resolution remote sensing images is proposed based on the optimization of U-Net3+ network. At the encoder end, the window attention embedding module is introduced layer by layer from the depth feature to the shallow layer, and the local attention from the deeper feature is gradually embedded into the lower-level feature to improve the semantic comprehension ability of the feature map. The TA-ASPP module, which combines threshold attention and depth separability, is introduced, which effectively improves the extraction efficiency of feature information. The multi-scale fusion module is modified on the decoder side, and the learnable dense upsampling convolution and deep separation convolution are used to replace the original bilinear interpolation and ordinary convolution, which significantly reduces the computational complexity while ensuring the accuracy. The dataset consists of parts of Chongqing city under different scenarios. Experimental results show that the TA-UNet3+ network model is better than the semantic segmentation network in terms of accuracy, recall, F1 and IoU, and shows higher surface water extraction accuracy.

Key words: surface water extraction, remote sensing images, TA-UNet3+, threshold attention, dense upsampling convolution, TA-ASPP module, window attention

白倩, 罗小波, 母仕林. 基于TA-UNet3+的高分辨率遥感图像地表水体提取[J]. 计算机工程与应用, 2025, 61(13): 245-255.

BAI Qian, LUO Xiaobo, MU Shilin. Surface Water Extraction from High-Resolution Remote Sensing Images Based on TA-UNet3+[J]. Computer Engineering and Applications, 2025, 61(13): 245-255.

参考文献

[1] AL-KHALDI M M, JOHNSON J T, GLEASON S, et al. Inland water body mapping using CYGNSS coherence detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(9): 7385-7394.
[2] EL-ALEM A, CHOKMANI K, LAURION I, et al. Ensemble-based systems to monitor algal bloom with remote sensing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(10): 7955-7971.
[3] LUO X, LI X X, WU Y X, et al. Research on change detection method of high-resolution remote sensing images based on subpixel convolution[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 14: 1447-1457.
[4] HE X, CHEN Y S, HUANG L B. Bayesian deep learning for hyperspectral image classification with low uncertainty[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5506916.
[5] ZHU X X, TUIA D, MOU L C, et al. Deep learning in remote sensing: a comprehensive review and list of resources[J]. IEEE Geoscience and Remote Sensing Magazine, 2017, 5(4): 8-36.
[6] LIN H N, SHI Z W, ZOU Z X. Fully convolutional network with task partitioning for inshore ship detection in optical remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(10): 1665-1669.
[7] FENG W Q, SUI H G, HUANG W M, et al. Water body extraction from very high-resolution remote sensing imagery using deep U-Net and a superpixel-based conditional random field model[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(4): 618-622.
[8] LI R R, LIU W J, YANG L, et al. DeepUNet: a deep fully convolutional network for pixel-level sea-land segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(11): 3954-3962.
[9] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.
[10] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 6230-6239.
[11] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
[12] CHEN L C, ZHU Y K, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer, 2018: 833-851.
[13] MA D L, LIU B Z, HUANG Q J, et al. MwdpNet: towards improving the recognition accuracy of tiny targets in high-resolution remote sensing image[J]. Scientific Reports, 2023, 13(1): 13890.
[14] DAI M C, LENG X G, XIONG B L, et al. An efficient water segmentation method for SAR images[C]//Proceedings of the 2020 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2020: 1129-1132.
[15] YU C Q, WANG J B, PENG C, et al. BiSeNet: bilateral segmentation network for real-time semantic segmentation[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer, 2018: 334-349.
[16] DIRSCHERL M, DIETZ A J, KNEISEL C, et al. A novel method for automated supraglacial lake mapping in Antarctica using sentinel-1 SAR imagery and deep learning[J]. Remote Sensing, 2021, 13(2): 197.
[17] REN Y B, LI X F, YANG X F, et al. Development of a dual-attention U-Net model for sea ice and open water classification on SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19: 4010205.
[18] LIU Z H, CHEN X M, ZHOU S P, et al. DUPnet: water body segmentation with dense block and multi-scale spatial pyramid pooling for remote sensing images[J]. Remote Sensing, 2022, 14(21): 5567.
[19] MIAO R, REN T C, ZHOU K, et al. A method of water body extraction based on multiscale feature and global context information[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 12138-12152.
[20] QI H C, KONG X W, CHENG L, et al. Addressing fine-grained lake water body extraction: a hybrid approach combining vision transformer and geodesic active contour[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 4204614.
[21] WANG R F, ZHANG C C, CHEN C, et al. A multi-modality fusion and gated multi-filter U-Net for water area segmentation in remote sensing[J]. Remote Sensing, 2024, 16(2): 419.
[22] WEI D B, XIE H J, LI P R, et al. A learning framework with multispectral band-differentiated encoding for remote sensing water body detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 6278-6289.
[23] HUANG H M, LIN L F, TONG R F, et al. UNet 3+: a full-scale connected UNet for medical image segmentation[C]//Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2020: 1055-1059.
[24] SIMONYAN K, ZISSERMAN A J C S. Very deep convolutional networks for large-scale image recognition[J]. arXiv: 1409.1556, 2014.
[25] WANG P Q, CHEN P F, YUAN Y, et al. Understanding convolution for semantic segmentation[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2018: 1451-1460.
[26] LONG W, ZHANG Y J, CUI Z W, et al. Threshold attention network for semantic segmentation of remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 4600312.
[27] KANG J, GUAN H Y, MA L F, et al. WaterFormer: a coupled transformer and CNN network for waterbody detection in optical remotely-sensed imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 206: 222-241.