基于深度学习的高分遥感图像建筑物识别

doi:10.3969/j.issn.0255-8297.2024.03.001

摘要/Abstract

摘要： 该文面向高分遥感图像建筑物深度学习检测与识别的具体需求，在归纳和分析现有深度学习与建筑物提取方法的基础上，重点探讨了高分遥感图像建筑物深度学习识别方法和深度学习识别系统，并探讨了未来可能的研究方向。所提方法将为高分遥感图像深度学习目标检测中样本库和遥感数据库的建设提供参考，为利用深度学习开展多尺度、多源高分遥感建筑物检测与识别提供支持。

关键词: 建筑物识别, 高分遥感图像, 卷积神经网络, 样本集, 数据集

Abstract: This paper focuses on deep learning methods for detection and recognition of the buildings in the high-resolution remote sensing images. It provides a summary and analysis of the existing deep learning and building extraction methods and highlights future research directions. The study aims to contribute to the construction of sample libraries and remote sensing databases for deep learning-based target detection in high-resolution remote sensing images. This study can provide a reference for the construction of sample libraries and remote sensing databases for the deep learning-based target detection of highresolution remote sensing images. It also supports the building detection and recognition by deep learning in multi-scale and multi-source high-resolution remote sensing.

Key words: building recognition, high-resolution remote sensing image, convolutional neural networks (CNN), sample data, data set

中图分类号:

TP751.1

李成范, 孟令奎, 刘学锋. 基于深度学习的高分遥感图像建筑物识别[J]. 应用科学学报, 2024, 42(3): 375-387.

LI Chengfan, MENG Lingkui, LIU Xuefeng. Building Recognition of High-Resolution Remote Sensing Images Based on Deep Learning[J]. Journal of Applied Sciences, 2024, 42(3): 375-387.

参考文献

[1] 胡娟, 杨厚群, 杜欣然, 等. 小样本学习在高分遥感影像分类与识别中的应用[J]. 重庆邮电大学学报(自然科学版), 2022, 34(3): 410-422. Hu J, Yang H Q, Du X R, et al. Application of few-shot learning in high resolution remote sensing image classification and recognition [J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2022, 34(3): 410-422. (in Chinese)
[2] Yao X D, Guo Q, Li A. Light-weight cloud detection network for optical remote sensing images with attention-based Deeplab V3+ architecture [J]. Remote Sensing, 2021, 13(18): 3617.
[3] 叶利华, 王磊, 张文文, 等. 高分辨率光学遥感场景分类的深度度量学习方法[J]. 测绘学报, 2019, 48(6): 698-707. Ye L H, Wang L, Zhang W W, et al. Deep metric learning method for high resolution sensing image scene classification [J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(6): 698-707. (in Chinese)
[4] Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors [J]. Nature, 1986, 323(6088): 533-536.
[5] 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.
[6] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2012, 60: 84-90.
[7] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [DB/OL]. 2014[2023-03-21]. https://arxiv.org/abs/1409.1556.
[8] Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 1-9.
[9] Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-resNet and the impact of residual connections on learning [DB/OL]. 2016[2023-03-21]. https://arxiv.org/abs/1602.07261.
[10] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 3431-3440.
[11] Liu W, Rabinovich A, Berg A C. ParseNet: looking wider to see better [DB/OL]. 2015[2023-03-21]. https://arxiv.org/abs/1506.04579.
[12] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 770-778.
[13] Zhang H, Wu C, Zhang Z, et al. ResNeSt: split-attention networks [DB/OL]. 2020[2023-03- 21]. https://arxiv.org/abs/2004.08955.
[14] Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks [DB/OL]. 2016[2023-03-21]. https://arxiv.org/abs/1608.06993.
[15] Sabour S, Frosst N, Hinton G E. Dynamic routing between capsules [DB/OL]. 2017[2023- 03-21]. https://arxiv.org/abs/1710.09829.
[16] Gao S H, Cheng M M, Zhao K, et al. Res2Net: a new multi-scale backbone architecture [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652-662.
[17] 刘媛. 高分辨率遥感影像建筑物屋顶识别方法研究[D]. 北京: 北京建筑大学, 2021.
[18] 林祥国, 张继贤, 李海涛, 等. 基于T型模板匹配半自动提取高分辨率遥感影像带状道路[J]. 武汉大学学报(信息科学版), 2009, 34(3): 293-296. Lin X G, Zhang J X, Li H T, et al. Semi-automatic extraction of ribbon road from high resolution remotely sensed imagery by a T-shaped template matching [J]. Geomatics and Information Science of Wuhan University, 2009, 34(3): 293-296.(in Chinese)
[19] Wentz E A, Nelson D, Rahman A, et al. Expert system classification of urban land use/cover for Delhi, India [J]. International Journal of Remote Sensing, 2008, 29(15): 4405-4427.
[20] 王芬, 郭擎, 葛小青. 深度递归残差网络的遥感图像空谱融合[J]. 遥感学报, 2021, 25(6): 1244-1256. Wang F, Guo Q, Ge X Q. Pan-sharpening by deep recursive residual network [J]. National Remote Sensing Bulletin, 2021, 25(6): 1244-1256.(in Chinese)
[21] 候玉婷, 王书功, 南卓铜. 基于知识规则的土地利用/土地覆被分类方法: 以黑河流域为例[J]. 地理学报, 2011, 66(4): 549-561. Hou Y T, Wang S G, Nan Z T. A rule-based land cover classification method for the Heihe River basin [J]. Acta Geographica Sinica, 2011, 66(4): 549-561.(in Chinese)
[22] Celik T. Unsupervised change detection in satellite images using principal component analysis and K-means clustering [J]. IEEE Geoscience and Remote Sensing Letters, 2009, 6(4): 772-776.
[23] Huang X, Zhang L P. 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.
[24] Rodriguez-Galiano V F, Ghimire B, Rogan J, et al. An assessment of the effectiveness of a random forest classifier for land-cover classification [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 67: 93-104.
[25] 骆剑承, 吴田军, 夏列钢. 遥感图谱认知理论与计算[J]. 地球信息科学学报, 2016, 18(5): 578-589. Luo J C, Wu T J, Xia L G. The theory and calculation of spatial-spectral cognition of remote sensing [J]. Journal of Geo-Information Science, 2016, 18(5): 578-589.(in Chinese)
[26] Guo Q, Li S J, Li A. An efficient dual spatial-spectral fusion network [J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-13.
[27] 周成虎, 骆剑承, 陈秋晓, 等. 遥感影像地学理解与分析[M]. 北京: 科学出版社, 1999.
[28] Blaschke T, Hay G J, Kelly M, et al. Geographic object-based image analysis-towards a new paradigm [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87: 180-191.
[29] Blaschke T. Object based image analysis for remote sensing [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 65(1): 2-16.
[30] 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. Gong J Y, Ji S P. Photogrammetry and deep learning [J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(6): 693-704. (in Chinese)
[31] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation [J]. 2015[2023-03-21]. https://arxiv.org/abs/1505.04597.
[32] Girshick R. Fast R-CNN [DB/OL]. 2015[2023-03-21]. https://arxiv.org/abs/1504.08083.
[33] Girshick R, Donahue J, Darrell T, et al. Region-based convolutional networks for accurate object detection and segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 142-158.
[34] 江一帆, 于海洋, 李朝亮, 等. 基于改进Faster R-CNN的高分遥感影像储油罐检测与信息提取[J]. 遥感信息, 2020, 35(4): 89-96. Jiang Y F, Yu H Y, Li C L, et al. Oil storage tank detection and information extraction from high-resolution remote sensing imagery based on improved Faster R-CNN [J]. Remote Sensing Information, 2020, 35(4): 89-96. (in Chinese)
[35] 林娜, 冯丽蓉, 张小青. 基于优化Faster R-CNN的遥感影像飞机检测[J]. 遥感技术与应用, 2021, 36(2): 275-284. Lin N, Feng L R, Zhang X Q. Aircraft detection in remote sensing image based on optimized Faster R-CNN [J]. Remote Sensing Technology and Application, 2021, 36(2): 275-284.(in Chinese)
[36] Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [DB/OL]. 2015[2023-03-21]. https://arxiv.org/abs/1506.01497.
[37] Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection [DB/OL]. 2015[2023-03-21]. https://arxiv.org/abs/1506.02640.
[38] He K M, Gkioxari G, Dollár P, et al. Mask R-CNN [C]//IEEE International Conference on Computer Vision (ICCV), 2017: 2961-2969.
[39] 彭宝钗, 郑成. 基于深度学习的建筑物检测方法[J]. 电脑编程技巧与维护, 2022(2): 136-138. Peng B C, Zheng C. Building detection method based on deep learning [J]. Computer Programming Skills & Maintenance, 2022(2): 136-138. (in Chinese)
[40] Lu T T, Ming D P, Lin X G, et al. Detecting building edges from high spatial resolution remote sensing imagery using richer convolution features network [J]. Remote Sensing, 2018, 10(9): 1496-1500.
[41] 左俊皓, 赵聪, 朱晓龙, 等. Faster-RCNN和Level-Set结合的高分遥感影像建筑物提取[J]. 液晶与显示, 2019, 34(4): 439-447. Zuo J H, Zhao C, Zhu X L, et al. High-resolution remote sensing image building extraction combined with faster-RCNN and level-set [J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(4): 439-447.(in Chinese)
[42] Sun G, Huang H, Weng Q, et al. Combinational shadow index for building shadow extraction in urban areas from Sentinel-2A MSI imagery [J]. International Journal of Applied Earth Observation and Geoinformation, 2019, 78(2): 53-65.
[43] Garcia-Garcia A, Orts-Escolano S, Oprea S, et al. A review on deep learning techniques applied to semantic segmentation [DB/OL]. 2017[2023-03-21]. https://arxiv.org/abs/1704.06857.
[44] 胡敏, 况润元, 王利花, 等. 基于BP神经网络的SAR海表风场反演: 以长江入海口及临近海域为例 [J]. 海洋湖沼通报, 2020, 35(2): 35-42. Hu M, Kuang R Y, Wang L H, et al. Retrieval of sea surface wind field of SAR based on BP neural network-taking the Yangtze River estuary with its adjacent seas as an example [J]. Transactions of Oceanology and Limnology, 2020, 35(2): 35-42. (in Chinese)
[45] 刘亦凡, 张秋昭, 王光辉, 等. 利用深度残差网络的遥感影像建筑物提取[J]. 遥感信息, 2020, 35(2): 59-64. Liu Y F, Zhang Q Z, Wang G H, et al. Building extraction in remote sensing imagery based on deep residual network [J]. Remote Sensing Information, 2020, 35(2): 59-64. (in Chinese)
[46] 李志强. 基于深度学习的城市建筑物提取方法研究[D]. 北京: 北京建筑大学, 2019.
[47] 宋师然. 高分遥感城市建筑物对象化识别方法研究[D]. 北京: 北京建筑大学, 2020.
[48] 胡舒, 王树根, 王越, 等. 基于Mask R-CNN的高分遥感影像建筑物目标检测算法[J]. 测绘地理信息, 2023, 48(3): 50-54. Hu S, Wang S G, Wang Y, et al. Building object detection in high-resolution remote sensing image based on Mask R-CNN [J]. Journal of Geomatics, 2023, 48(3): 50-54. (in Chinese)
[49] 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. Ji S P, Wei S Q. Building extraction via convolutional neural networks from an open remote sensing building dataset [J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(4): 448-459. (in Chinese)
[50] 吴樊, 张红，王超，等. SARBuD 1.0: 面向深度学习的GF-3精细模式SAR建筑数据集[J]. 遥感学报, 2022, 26(4): 620-631. Wu F, Zhang H, Wang C, et al. SARBuD1.0: a SAR building dataset based on GF-3 FSII imageries for built-up area extraction with deep learning method [J]. National Remote Sensing Bulletin, 2022, 26(4): 620-631. (in Chinese)
[51] 龚健雅, 许越, 胡翔云, 等. 遥感影像智能解译样本库现状与研究[J]. 测绘学报, 2021, 50(8): 1013- 1022. Gong J Y, Xu Y, Hu X Y, et al. Status analysis and research of sample database for intelligent interpretation of remote sensing image [J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8): 1013-1022. (in Chinese)
[52] 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.
[53] Long Y, Xia G S, Li S, et al. On creating benchmark dataset for aerial image interpretation: reviews, guidances and million-AID [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 4205-4230.