高分辨率遥感影像可为像素级的建筑物提取工作提供更高质量的数据源。近年来，深度学习技术高速发展，也为遥感影像的建筑物提取工作带来了新的分割方法。然而，受不同自然、文化以及社会发展程度的影响，建筑物的形态与分布存在一定差异，这使得网络在提取影像中不同区域的建筑物时，难以取得稳定的分割效果。此外，因遥感影像中地物光谱信息复杂，其对多尺度建筑物的提取细节也会产生不同程度的影响。为此，本文利用高分辨率遥感影像作为数据源，同时结合语义分割技术以及遥感图像处理技术，来探究具有更高精度和分割效果的建筑物提取方法。具体研究工作如下：

（1）本文选取了中国陕西省西安市的部分区域作为研究区，并采用国产高分二号卫星影像构建了一套地物背景信息复杂，且建筑物形态、分布以及尺度多样的西安建筑物数据集。该数据集影像中包含了红、绿、蓝以及近红外四个波段，可为多种光谱信息处理方式提供数据支持。此外，通过与武汉大学建筑物数据集、马萨诸塞州建筑物数据集开展的质量分析实验可知，本文自建的西安建筑物数据集具有一定的可行性，且能够让语义分割网络有效地学习影像中的建筑物特征信息，丰富了用于建筑物提取的数据集多样性。

（2）构建了一种融合多种注意力机制的并行编码建筑物提取网络。该网络在总体上由编码器和解码器构成。在编码器中，采用了深度卷积神经网络与Transformer的并行编码结构，以发挥它们对局部和全局特征信息的提取优势；在网络的不同深度位置，针对性的引入了坐标注意力机制和空间通道注意力机制来桥接编码器和解码器，以保留编码过程中更为丰富的空间和语义特征信息；引入密集型空洞特征金字塔池化，从而在解码过程中的各层上采样部分捕获更多尺度的上下文信息。在西安、武汉大学和马萨诸塞州建筑物数据集上开展了消融实验，验证了本文提出网络中各结构的有效性。通过在三种实验数据集上开展所提出网络与U-Net、ResUNet++、DeepLabv3+、Swin-Unet和UNetFormer的对比实验，证明了该网络的优势性与泛化性。本研究所提出网络的F1分数得分在三种建筑物数据集上分别为93.34%、94.52%和82.59%，边界交并比得分分别为80.57%、60.39%和67.06%。

（3）设计了一种增强高分辨率遥感影像建筑物光谱信息的模块。首先，该模块计算了比值运算，并利用ReliefF算法筛选了影像的红、绿、蓝、近红外波段以及比值运算结果中特征权值最大的几组。而后，利用最小噪声比率变换将形态学建筑物指数赋予给ReliefF筛选出的结果。通过上述操作强调了影像中多波段间的信息关联，并赋予了它们更强的建筑物形态学特征，以此来提升语义分割网络的建筑物提取效果。在西安数据集上对所提出模块开展了性能实验，验证了该模块的有效性和泛化性。采用该模块进行影像处理后，本文所提出网络的F1分数和边界交并比指标分别提升至94.10%和82.13%。

High-resolution remote sensing images can provide higher-quality data sources for pixel-level building extraction. In recent years, the rapid development of deep learning technology has also brought new segmentation methods for building extraction in remote sensing images. However, due to the influence of different natural, cultural, and social development levels, there are certain differences in the shape and distribution of buildings, which makes it difficult for the network to obtain a stable segmentation effect when extracting buildings in different regions of the image. In addition, due to the complex spectral information of ground objects in remote sensing images, it will also have different degrees of influence on the extraction details of multi-scale buildings. To this end, this paper uses high-resolution remote sensing images as the data source, combining both semantic segmentation techniques and remote sensing image processing techniques to explore building extraction methods with higher accuracy and segmentation effects. Specific research work is as follows:

(1) In this paper, part of Xi'an City, Shaanxi Province, China, is selected as the study area, and a set of Xi'an building dataset with complex feature background information and diverse building forms, distributions, and scales is constructed by using domestic Gaofen-2 satellite images. The dataset contains images in the red, green, blue, and near-infrared bands, which can provide data support for a variety of spectral information processing methods. In addition, through the quality analysis experiments with the WHU building dataset and the Massachusetts building dataset, we can see that the Xi'an building dataset built by ourselves in this paper has certain feasibility, and can enable the semantic segmentation network to effectively learn the building feature information in the image, and enrich the diversity of the data set used for building extraction.

(2) A parallel encoded building extraction network incorporating multiple attention mechanisms is constructed. The network in general consists of an encoder and a decoder. In the encoder, a parallel coding structure of the deep convolutional neural network and Transformer is employed to take advantage of their feature extraction of local and global feature information; at different depths, positions of the network, the Coordinate Attention, and the Convolutional Block Attention Module are introduced to bridge the encoder and decoder in a targeted manner to retain richer spatial and semantic feature information during the coding process; Introducing Dense Atrous Spatial Pyramid Pooling to capture more scale context information in each layer sampling part of the decoding process. Ablation experiments are carried out on the Xi'an, WHU, and Massachusetts building datasets to verify the effectiveness of the proposed network on each structure. The superiority and generalization of the proposed network are demonstrated by carrying out comparison experiments of this network with U-Net, ResUNet++, DeepLabv3+, Swin-Unet, and UNetFormer on three experimental datasets. On three building datasets, F1 Scores of the proposed network are 93.34%, 94.52%, and 82.59%. Boundary IoUs are 80.57%, 60.39%, and 67.06%.

(3) A module was designed to enhance the spectral information of buildings from high-resolution remote sensing images. First, the module calculates the ratio calculation and uses the ReliefF algorithm to screen the red, green, blue, and near-infrared bands and the groups with the largest feature weights in the ratio calculation results. Then, the morphologic building index is assigned to the results of ReliefF by using the minimum noise ratio transformation. The above operations emphasize the information correlation among the multi-bands in the image and give them stronger building morphological features, to improve the building extraction effect of the semantic segmentation network. Performance experiments on the proposed module are carried out on the Xi'an dataset to verify the effectiveness and generalization of the module. After using the module for image processing, the F1 Score and Boundary IoU of the proposed network are improved to 94.10% and 82.13%, respectively.

[1] 吕少云, 李佳田, 阿晓荟, 等. Res_ASPP_UNet++：结合分离卷积与空洞金字塔的遥感影像建筑物提取网络[J]. 遥感学报, 2023, 27(2): 502-519.

[2] 胡明洪, 李佳田, 姚彦吉, 等. 结合多路径的高分辨率遥感影像建筑物提取SER-UNet算法[J]. 测绘学报, 2022, 52(5): 808-817.

[3] Li X, Ying Y, Xu X, et al. Identifying key determinants for building energy analysis from urban building datasets[J]. Building and Environment, 2020, 181: 107114.

[4] Yuan P, Zhao Q, Zhao X, et al. A transformer-based Siamese network and an open optical dataset for semantic change detection of remote sensing images[J]. International Journal of Digital Earth, 2022, 15(1): 1506-25.

[5] Shugar D H, Jacquemart M, Shean D, et al. A massive rock and ice avalanche caused the 2021 disaster at Chamoli, Indian Himalaya[J]. Science, 2021, 373(6552): 300-306.

[6] Li D, Lu X, Walling D E, et al. High Mountain Asia hydropower systems threatened by climate-driven landscape instability[J]. Nature Geoscience, 2022, 15(7): 520-530.

[7] Pang L, Sun J, Chi Y, et al. CD-TransUNet: a hybrid transformer network for the change detection of urban buildings using l-band SAR images[J]. Sustainability, 2022, 14(16): 9847.

[8] Ding Q, Shao Z, Huang X, et al. DSA-Net: A novel deeply supervised attention-guided network for building change detection in high-resolution remote sensing images[J]. International Journal of Applied Earth Observation and Geoinformation, 2021, 105: 102591.

[9] Liu M, Chai Z, Deng H, et al. A CNN-transformer network with multiscale context aggregation for fine-grained cropland change detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 4297-4306.

[10] Wang T, Shi Q, Nikkhoo M, et al. The rise, collapse, and compaction of Mt. Mantap from the 3 September 2017 North Korean nuclear test[J]. Science, 2018, 361(6398): 166-170.

[11] Cao S, Weng Q, Du M, et al. Multi-scale three-dimensional detection of urban buildings using aerial LiDAR data[J]. GIScience & Remote Sensing, 2020, 57(8): 1125-1143.

[12] Zhang Y, Peng D, Huang X. Object-based change detection for VHR images based on multiscale uncertainty analysis[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 15(1): 13-17.

[13] Zhu Q, Guo X, Li Z, et al. A review of multi-class change detection for satellite remote sensing imagery[J]. Geo-Spatial Information Science, 2022, 27(1): 1-15.

[14] 路慧. 基于高分辨率遥感影像语义分割的建筑物自动提取方法研究[D]. 南京: 南京信息工程大学, 2022.

[15] Yang H, Yu B, Luo J, et al. Semantic segmentation of high spatial resolution images with deep neural networks[J]. GIScience & Remote Sensing, 2019, 56(5): 749-768.

[16] Zheng H, Gong M, LIU T, et al. HFA-Net: High frequency attention siamese network for building change detection in VHR remote sensing images[J]. Pattern Recognition, 2022, 129: 108717.

[17] Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.

[18] Bradbury K, Brigman B, Collins L, et al. Aerial imagery object identification dataset for building and road detection, and building height estimation[J]. Figshare, 2016.

[19] 季顺平, 魏世清. 遥感影像建筑物提取的卷积神经元网络与开源数据集方法[J]. 测绘学报, 2019, 48(4): 448-459.

[20] Maggiori E, Tarabalka Y, Charpiat G, et al. Can semantic labeling methods generalize to any city? the inria aerial image labeling benchmark[C]//Proceedings of the IEEE International Geoscience and Remote Sensing Symposium. Barcelona, Spain, 2017: 3226-3229.

[21] Mnih V. Machine learning for aerial image labeling[M]. University of Toronto (Canada), 2013.

[22] Chen Q, Wang L, Wu Y, et al. TEMPORARY REMOVAL: Aerial imagery for roof segmentation: A large-scale dataset towards automatic mapping of buildings[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 147: 42-55.

[23] 龙丽红, 朱宇霆, 闫敬文, 等. 新型语义分割D-UNet的建筑物提取[J]. 遥感学报, 2023, 27(11): 2593-2602.

[24] 张媛, 张杰林, 赵学胜, 等. 高分辨率遥感影像的建筑物轮廓信息提取方法[J]. 国土资源遥感, 2015, 27(3): 52-58.

[25] 吴目宇. 多尺度特征融合的高分辨率遥感影像建筑物自动提取[D]. 武汉: 武汉大学, 2024.

[26] 邢云飞, 刘萍, 谢育珽, 等. 基于高分辨率遥感影像的面向对象建筑物分级提取方法[J]. 航天返回与遥感, 2023, 44(4): 88-102.

[27] 周绍光, 孙金彦, 凡莉, 等. 高分辨率遥感影像的建筑物轮廓信息提取方法[J]. 国土资源遥感, 2015, 27(3): 52-58.

[28] 班瑞, 郑延召. 一种高分辨率遥感影像中的建筑物快速提取方法[P]. 中国专利: CN105719306B, 2024-04-25.

[29] 尹峰, 祁琼, 许博文. 基于角点的高分辨率遥感影像建筑物提取[J]. 地理空间信息, 2018, 16(10): 58-61.

[30] Vincent L, Soille P. Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6): 583-598.

[31] 魏德强. 高分辨率遥感影像建筑物提取技术研究[D]. 郑州: 解放军信息工程大学, 2013.

[32] 任晓娟, 肖双九, 彭小朋. 基于改进分水岭变换的遥感图像建筑物提取[J]. 计算机应用与软件, 2011, 28(12): 249-252.

[33] 赵宗泽, 张永军. 基于植被指数限制分水岭算法的机载激光点云建筑物提取[J]. 光学学报, 2016, 36(10): 503-511.

[34] Huang X, Zhang L. An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classification of High-Resolution Remotely Sensed Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1): 257-272.

[35] 胡荣明, 黄小兵, 黄远程. 增强形态学建筑物指数应用于高分辨率遥感影像中建筑物提取[J]. 测绘学报, 2014, 43(5): 514-520.

[36] Cheng G, Han J. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117: 11-28.

[37] Jiménez L I, Plaza J, Plaza A. Efficient implementation of morphological index for building/shadow extraction from remotely sensed images[J]. Journal of Supercomputing, 2017, 73(1): 482-494.

[38] 洪亮, 冯亚飞, 彭双云, 等. 面向对象的多尺度加权联合稀疏表示的高空间分辨率遥感影像分类[J]. 测绘学报, 2022, 51(2): 224-237.

[39] LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

[40] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the conference on Learning Representations. 2014.

[41] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.

[42] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//Proceedings of the Medical Image Computing and Computer-Assisted Intervention. Springer, 2015: 234-241.

[43] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Computer Vision and Pattern Recognition. Las Vegas, 2016: 770-778.

[44] 龚健雅, 季顺平. 摄影测量与深度学习[J]. 测绘学报, 2018, 47(6): 693-704.

[45] Tejeswari B, Sharma S K, Kumar M, et al. Building footprint extraction from space-borne imagery using deep neural networks[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022, 43: 641-647.

[46] Shao Z, Tang P, Wang Z, et al. BRRNet: A fully convolutional neural network for automatic building extraction from high-resolution remote sensing images[J]. Remote Sensing, 2020, 12(6): 1050.

[47] Jin Y, Xu W, Zhang C, et al. Boundary-aware refined network for automatic building extraction in very high-resolution urban aerial images[J]. Remote Sensing, 2021, 13(4): 692.

[48] Yang M, Yu K, Zhang C, et al. Denseaspp for semantic segmentation in street scenes[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 3684-3692.

[49] Si Z, Zhou B, Wang B, et al. High-resolution remote sensing building extraction based on attention mechanism and DeepLabv3+[C]//Proceedings of the international conference on Computer Information Science and Application Technology. SPIE, 2022, 12451: 122-126.

[50] 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, 2017, 40(4): 834-848.

[51] Xu X, Zhang H, Ran Y, et al. High-precision segmentation of buildings with small sample sizes based on transfer learning and multi-scale fusion[J]. Remote Sensing, 2023, 15(9): 2436.

[52] Yu W, Liu B, Liu H, et al. Recurrent residual deformable conv unit and multi-head with channel self-attention based on U-Net for building extraction from remote sensing images[J]. Remote Sensing, 2023, 15(20): 5048.

[53] 何直蒙, 丁海勇, 安炳琪. 高分辨率遥感影像建筑物提取的空洞卷积E-Unet算法[J]. 测绘学报, 2022, 51(03): 457-467.

[54] Wang Z, Xu N, Wang B, et al. Urban building extraction from high-resolution remote sensing imagery based on multi-scale recurrent conditional generative adversarial network[J]. GIScience & Remote Sensing, 2022, 59(1): 861-884.

[55] Shi X, Huang H, Pu C, et al. CSA-UNet: channel-spatial attention-based encoder-decoder network for rural blue-roofed building extraction from UAV Imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1-5.

[56] Zhu Q, Liao C, Hu H, et al. MAP-Net: Multiple attending path neural network for building footprint extraction from remote sensed imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 59(7): 6169-6181.

[57] Zhou Z, Rahman Siddiquee M M, Tajbakhsh N, et al. UNet++: A nested U-Net architecture for medical image segmentation[C]//Proceedings of the Medical Image Computing and Computer-Assisted Intervention. Granada, Spain, 2018: 3-11.

[58] Aryal J, Neupane B. Multi-scale feature map aggregation and supervised domain adaptation of fully convolutional networks for urban building footprint extraction[J]. Remote Sensing, 2023, 15(2): 488.

[59] Wang L, Fang S, Meng X, et al. Building extraction with vision transformer[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-11.

[60] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.

[61] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929, 2020.

[62] Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF international conference on Computer Vision. Montreal, 2021: 10012-10022.

[63] Chen X, Qiu C, Guo W, et al. Multiscale feature learning by transformer for building extraction from satellite images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 1-5.

[64] Zheng S, Lu J, Zhao H, et al. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2021: 6881-6890.

[65] Xie E, Wang W, Yu Z, et al. SegFormer: Simple and efficient design for semantic segmentation with transformers[J]. Computing Research Repository, 2021: 12077-12090.

[66] Cao H, Wang Y, Chen J, et al. Swin-unet: Unet-like pure transformer for medical image segmentation[C]//Proceedings of the European conference on Computer Vision. Springer, Cham, 2022: 205-218.

[67] Gao G, Wang Z, Li J, et al. Lightweight bimodal network for single-image super-resolution via symmetric CNN and recursive transformer[C]//Proceedings of the European conference on Artificial Intelligence, 2022: 913-919.

[68] Zhang Y, Liu H, Hu Q. Transfuse: Fusing transformers and cnns for medical image segmentation[C]//Proceedings of the Medical Image Computing and Computer Assisted Intervention, 2021: 14-24.

[69] Wang L, Li R, Zhang C, et al. UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 190: 196-214.

[70] Zhang C, Jiang W, Zhang Y, et al. Transformer and CNN hybrid deep neural network for semantic segmentation of very-high-resolution remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-20.

[71] Wang W, Tan X, Zhang P, et al. A CBAM based multiscale transformer fusion approach for remote sensing image change detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 6817-6825.

[72] Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the conference on Computer Vision. Munich, 2018: 3-19.

[73] He X, Zhou Y, Zhao J, et al. Swin transformer embedding unet for remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-15.

[74] Li M, Rui J, Yang S, et al. Method of building detection in optical remote sensing images based on segformer[J]. Sensors, 2023, 23(3): 1258.

[75] 成嘉伟, 郭荣佐, 吴建成. 双分支特征融合的遥感建筑物检测模型[J]. 计算机工程与应用, 2024: 1-10.

[76] Shang R, Zhang J, Jiao L, et al. Multi-scale adaptive feature fusion network for semantic segmentation in remote sensing images[J]. Remote Sensing, 2020, 12(5): 872.

[77] Gao L, Liu H, Yang M, et al. STransFuse: Fusing swin transformer and convolutional neural network for remote sensing image semantic segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 10990-11003.

[78] Xia L, Mi S, Zhang J, et al. Dual-stream feature extraction network based on CNN and Transformer for building extraction[J]. Remote Sensing, 2023, 15(10): 2689.

[79] 张云佐, 郭威, 武存宇. 融合CNN和Transformer的遥感图像建筑物快速提取[J]. 光学精密工程, 2023, 31(11): 1700-1709.

[80] Chen K, Zou Z, Shi Z. Building extraction from remote sensing images with sparse token transformers[J]. Remote Sensing, 2021, 13(21): 4441.

[81] Yin X, Goudriaan J, Lantinga E A, et al. A flexible sigmoid function of determinate growth[J]. Annals of botany, 2003, 91(3): 361-371.

[82] Agarap A F. Deep learning using rectified linear units (relu)[J]. arXiv preprint arXiv:1803.08375, 2018.

[83] Fan E. Extended tanh-function method and its applications to nonlinear equations[J]. Physics Letters A, 2000, 277(4-5): 212-218.

[84] Jang E, Gu S, Poole B. Categorical reparameterization with gumbel-softmax[J]. arXiv preprint arXiv:1611.01144, 2016.

[85] Jha D, Smedsrud P H, Riegler M A, et al. Resunet++: An advanced architecture for medical image segmentation[C]//Proceedings of the International Symposium on Multimedia. San Diego, 2019: 225-2255.

[86] Huang H, Lin L, Tong R, et al. Unet 3+: A full-scale connected unet for medical image segmentation[C]//Proceedings of the IEEE international conference on Acoustics, Speech and Signal Processing. Barcelona, Spain, 2020: 1055-1059.

[87] Qin X, Zhang Z, Huang C, et al. U2-Net: Going deeper with nested U-structure for salient object detection[J]. Pattern recognition, 2020, 106: 107404.

[88] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018: 7132-7141.

[89] 于文玲. 基于编码解码的深度学习遥感影像建筑物提取研究[D]. 南昌: 华东理工大学, 2022.

[90] 杨栋杰, 高贤君, 冉树浩, 等. 基于多重多尺度融合注意力网络的建筑物提取[J]. 浙江大学学报(工学版), 2022, 56(10): 1924-1934.

[91] 江宝得, 黄威, 许少芬, 等. 融合分散自适应注意力机制的多尺度遥感影像建筑物实例细化提取[J]. 测绘学报, 2023, 52(9): 1504-1514.

[92] Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. Nashville, 2021: 13713-13722.

[93] Chen L C, Papandreou G, Schroff F, et al. Rethinking atrous convolution for semantic image segmentation[J]. arXiv preprint arXiv:170605587, 2017.

[94] Milletari F, Navab N, Ahmadi S A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of the IEEE international conference on 3D Vision. Stanford, 2016: 565-571.

[95] Sun L, Yin T, Ding W, et al. Multilabel feature selection using ML-ReliefF and neighborhood mutual information for multilabel neighborhood decision systems[J]. Information Sciences, 2020, 537: 401-24.

[96] 王振庆, 周艺, 王世新, 等. IEU-Net高分辨率遥感影像房屋建筑物提取[J]. 遥感学报, 2021, 25(11): 2245-2254.