面向城市功能区分类的光学遥感影像-OSM数据联合自监督学习方法

doi:10.11947/j.AGCS.2025.20240067

测绘学报 ›› 2025, Vol. 54 ›› Issue (1): 154-164.doi: 10.11947/j.AGCS.2025.20240067

• 摄影测量学与遥感 • 上一篇

面向城市功能区分类的光学遥感影像-OSM数据联合自监督学习方法

李佳铃¹(), 齐霁¹^,²^,³, 鲁伟鹏⁴, 陶超¹()

^1.中南大学地球科学与信息物理学院，湖南　长沙　410083
^2.广州大学地理科学与遥感学院，广东　广州　510006
^3.广州大学黄埔研究院，广东　广州　510000
^4.香港理工大学土地测量及地理资讯学系，香港　999077

收稿日期:2024-02-17 修回日期:2024-11-30 发布日期:2025-02-17
通讯作者: 陶超 E-mail:235011028@csu.edu.cn;kingtaochao@126.com
作者简介:李佳铃（2000—），女，硕士生，研究方向为高分辨率遥感影像智能解译，图像-语言模型驱动的遥感城市功能区分类。　E-mail：235011028@csu.edu.cn
基金资助:
湖南省杰出青年基金(2022JJ10072);国家自然科学基金(42171376)

Self-supervised learning based urban functional zone classification by integrating optical remote sensing image-OSM data

Jialing LI¹(), Ji QI¹^,²^,³, Weipeng LU⁴, Chao TAO¹()

^1.School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
^2.School of Geography and Remote Sensing, Guangzhou University, Guangzhou 510006, China
^3.Huangpu Research School of Guangzhou University, Guangzhou 510000, China
^4.Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong 999077, China

Received:2024-02-17 Revised:2024-11-30 Published:2025-02-17
Contact: Chao TAO E-mail:235011028@csu.edu.cn;kingtaochao@126.com
About author:LI Jialing (2000—), female, postgraduate, majors in semantic segmentation of high resolution remote sensing images based on deep learning, image-language model-driven remote sensing urban functional zone classification.　E-mail: 235011028@csu.edu.cn
Supported by:
The Natural Science Foundation of Hunan for Distinguished Young Scholars(2022JJ10072);The National Natural Science Foundation of China(42171376)

摘要/Abstract

摘要：

城市功能区的快速准确分类为城市规划和管理提供科学依据，有助于实现城市的可持续发展。尽管光学遥感影像提供了丰富的视觉信息，但其无法充分反映社会属性，易引发语义歧义。因此更多研究尝试联合使用包含城市社会属性的数据（如OSM数据）和光学遥感影像以期达到互补效果。但这一思路面临两个主要挑战：一是光学影像与OSM数据存在数据结构差异，传统的融合方法在特征提取阶段缺乏充分交互融合，导致模型难以充分学习数据之间的互补优势；二是随着模型学习使用的数据模态增多，训练一个稳定的模型需要更多的人工标注数据，但这显著提高了城市功能区分类模型应用的人力成本。针对上述问题，本文提出了一种面向城市功能区分类的光学遥感影像-OSM数据联合自监督学习方法。一方面，将OSM数据与光学影像在空间分布、数据结构等方面进行统一，然后在统一的多模态融合编码架构中进行特征提取和交互融合，以学习跨模态通用性表征。另一方面，采用自监督模型在大规模无标注数据上预训练，再通过少量标注数据将模型迁移到特定城市功能区分类任务中，从而减少人工成本。本文通过在北京、洛杉矶和伦敦3个大尺度区域进行城市功能区分类试验，证明了本文方法较现有主流方法的性能优势。

关键词: 城市功能区, 光学遥感影像, OSM, 自监督学习, 多模态

Abstract:

Rapid and accurate classification of urban functional zones (UFZs) provides a scientific basis for urban planning and management and helps to realize sustainable urban development. Although optical remote sensing images provide rich visual information, they cannot fully reflect social attributes and are prone to semantic ambiguity. Therefore, more studies have tried to jointly use data containing urban social attributes (e.g., OSM data) and optical remote sensing images to achieve complementary effects. However, this idea faces two main challenges: first, there are data structure differences between optical images and OSM data, and traditional fusion methods lack sufficient interaction and fusion in the feature extraction stage, which makes it difficult for the model to fully learn the complementary advantages between the data. Second, with the increase of data modalities used for model learning, more manually labeled data are required to train a stable model, but this significantly increases the labor cost of UFZ classification model application. In response to the above problems, this paper proposes a self-supervised learning based urban functional zone classification method by integrating optical remote sensing image-OSM data. On the one hand, OSM data are unified with optical images in terms of spatial distribution and data structure, and then feature extraction and interactive fusion are carried out in a unified multimodal fusion coding architecture to learn cross-modal generalized representations. On the other hand, in this paper, a self-supervised model is used to pre-train on large-scale unlabeled data, and then a small amount of labeled data is used to transfer the model to a specific UFZ classification task, thus reducing the labor cost. The performance advantages of this paper's method over existing mainstream methods are demonstrated by conducting UFZ classification experiments in three large-scale regions, Beijing, Los Angeles and London.

Key words: urban functional zone, optical remote sensing images, OSM, self-supervised learning, multimodality

中图分类号:

P237

李佳铃, 齐霁, 鲁伟鹏, 陶超. 面向城市功能区分类的光学遥感影像-OSM数据联合自监督学习方法[J]. 测绘学报, 2025, 54(1): 154-164.

Jialing LI, Ji QI, Weipeng LU, Chao TAO. Self-supervised learning based urban functional zone classification by integrating optical remote sensing image-OSM data[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(1): 154-164.

图/表 12

图1

图2

图3

图4

图5

图6

表1

表2

表3

图7

图8

表4

参考文献 32

[1]	杨小军. 城市遥感：城市环境监测、集成与建模[M]. 肖荣波，译. 北京: 高等教育出版社, 2015.
	YANG Xiaojun. Urban remote sensing: monitoring, synthesis and modeling in the urban environment[M]. XIAO Rongbo, trans. Beijing: Higher Education Press, 2015.
[2]	CHEN Lai, KANG Chaogui, YANG chao. Understanding citizens' emotion states under the urban livability environment through social media data: a case study of Wuhan[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(2): 49-59.
[3]	XIAO Zhifeng, LIU Qing, TANG Gefu, et al. Elliptic Fourier transformation-based histograms of oriented gradients for rotationally invariant object detection in remote-sensing images[J]. International Journal of Remote Sensing, 2015, 36(2): 618-644.
[4]	ZHU Qiqi, ZHONG Yanfei, ZHANG Liangpei. Multi-feature probability topic scene classifier for high spatial resolution remote sensing imagery[C]//Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec City: IEEE, 2014: 2854-2857.
[5]	WANG Kaijia, XU Weiming, LI Chuyu, et al. A study on the function and structure of mixed land use in urban built-up areas from the perspective of spatial governance[J]. Journal of Natural Resources, 2023, 38(6): 1496.
[6]	龚健雅, 张觅, 胡翔云, 等. 智能遥感深度学习框架与模型设计[J]. 测绘学报, 2022, 51(4): 475-487. DOI:. doi: 10.11947/j.AGCS.2022.20220027
	GONG Jianya, ZHANG Mi, HU Xiangyun, et al. The design of deep learning framework and model for intelligent remote sensing[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(4): 475-487. DOI:. doi: 10.11947/j.AGCS.2022.20220027
[7]	GUO Zhou, WEN Jiangtian, XU Rui. A shape and size free-CNN for urban functional zone mapping with high-resolution satellite images and POI data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5622117.
[8]	JOHNSON N, TREIBLE W, CRISPELL D. OpenSentinelMap: a large-scale land use dataset using OpenStreetMap and Sentinel-2 imagery[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. New Orleans: IEEE, 2022: 1332-1340.
[9]	LU Weipeng, TAO Chao, LI Haifeng, et al. A unified deep learning framework for urban functional zone extraction based on multi-source heterogeneous data[J]. Remote Sensing of Environment, 2022, 270: 112830.
[10]	GAO Mianxin, GUO Haijing, LIU Longwei, et al. Integrating street view imagery and taxi trajectory for identifying urban function of street space[J/OL]. Geo-spatial Information Science, 2024: 1-23[2023-12-10].https://doi.org/10.1080/10095020.2024.2311866.
[11]	SU Chen, HU Xinli, MENG Qingyan, et al. A multimodal fusion framework for urban scene understanding and functional identification using geospatial data[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 127: 103696.
[12]	ZHANG Yan, LIU Pengyuan, BILJECKI F. Knowledge and topology: a two layer spatially dependent graph neural networks to identify urban functions with time-series street view image[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 198: 153-168.
[13]	鲁伟鹏, 贺清康, 李佳铃, 等. 结合对象单元和Transformer网络的城市功能区分类[J]. 遥感学报, 2024, 28(8): 1927-1939.
	LU Weipeng, HE Qingkang, LI Jialing, et al. Object units and Transformer networks combined with urban functional zone classification method[J]. National Remote Sensing Bulletin, 2024, 28(8): 1927-1939.
[14]	WU Hao, LUO Wenting, LIN Anqi, et al. SALT: a multifeature ensemble learning framework for mapping urban functional zones from VGI data and VHR images[J]. Computers, Environment and Urban Systems, 2023, 100: 101921.
[15]	DU Shouji, DU Shihong, LIU Bo, et al. Large-scale urban functional zone mapping by integrating remote sensing images and open social data[J]. GIScience & Remote Sensing, 2020, 57(3): 411-430.
[16]	CAO Rui, TU Wei, YANG Cuixin, et al. Deep learning-based remote and social sensing data fusion for urban region function recognition[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 163: 82-97.
[17]	张良培, 何江, 杨倩倩, 等. 数据驱动的多源遥感信息融合研究进展[J]. 测绘学报, 2022, 51(7): 1317-1337. DOI:. doi: 10.11947/j.AGCS.2022.20220171
	ZHANG Liangpei, HE Jiang, YANG Qianqian, et al. Data-driven multi-source remote sensing data fusion: progress and challenges[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1317-1337. DOI:. doi: 10.11947/j.AGCS.2022.20220171
[18]	XU Shengyu, QING Linbo, HAN Longmei, et al. A new remote sensing images and point-of-interest fused (RPF) model for sensing urban functional regions[J]. Remote Sensing, 2020, 12(6): 1032.
[19]	CHEN Dongsheng, TU Wei, CAO Rui, et al. A hierarchical approach for fine-grained urban villages recognition fusing remote and social sensing data[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 106: 102661.
[20]	张兵, 杨晓梅, 高连如, 等. 遥感大数据智能解译的地理学认知模型与方法[J]. 测绘学报, 2022, 51(7): 1398-1415. DOI:. doi: 10.11947/j.AGCS.2022.20220279
	ZHANG Bing, YANG Xiaomei, GAO Lianru, et al. Geo-cognitive models and methods for intelligent interpretation of remotely sensed big data[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1398-1415. DOI:. doi: 10.11947/j.AGCS.2022.20220279
[21]	BAI Lubin, HUANG Weiming, ZHANG Xiuyuan, et al. Geographic mapping with unsupervised multi-modal representation learning from VHR images and POIs[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 201: 193-208.
[22]	ZAKERI F, MARIETHOZ G. A review of geostatistical simulation models applied to satellite remote sensing: methods and applications[J]. Remote Sensing of Environment, 2021, 259: 112381.
[23]	陶超, 阴紫薇, 朱庆, 等. 遥感影像智能解译：从监督学习到自监督学习[J]. 测绘学报, 2021, 50(8): 1122-1134. DOI:. doi: 10.11947/j.AGCS.2021.20210089
	TAO Chao, YIN Ziwei, ZHU Qing, et al. Remote sensing image intelligent interpretation: from supervised learning to self-supervised learning[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8): 1122-1134. DOI:. doi: 10.11947/j.AGCS.2021.20210089
[24]	TAO Chao, QI Ji, GUO Mingning, et al. Self-supervised remote sensing feature learning: learning paradigms, challenges, and future works[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-26.
[25]	BACHMANN R, MIZRAHI D, ATANOV A, et al. MultiMAE: multi-modal multi-task masked autoencoders[EB/OL]. [2023-12-10].https://arxiv.org/pdf/2204.01678.
[26]	中国城市规划设计研究院. 城市用地分类与规划建设用地标准：GB 50137—2011[S]. 北京: 中国建筑工业出版社, 2011.
	China Academy of Urban Planning and Design. Code for classification of urban land use and planning standards of development land: GB 50137—2011[S]. Beijing: China Architecture & Building Press, 2011.
[27]	HE Kaiming, CHEN Xinlei, XIE Saining, et al. Masked autoencoders are scalable vision learners[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 15979-15988.
[28]	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[EB/OL]. [2023-12-10].https://arxiv.org/pdf/2010.11929.
[29]	LIU Zhuang, MAO Hanzi, WU Chaoyuan, et al. A ConvNet for the 2020s[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 11966-11976.
[30]	ZHOU Wen, MING Dongping, LÜ Xianwei, et al. SO-CNN based urban functional zone fine division with VHR remote sensing image[J]. Remote Sensing of Environment, 2020, 236: 111458.
[31]	ZHAO Wenzhi, BO Yanchen, CHEN Jiage, et al. Exploring semantic elements for urban scene recognition: deep integration of high-resolution imagery and OpenStreetMap (OSM)[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 151: 237-250.
[32]	GUO Yiwen, TANG Jianbo, LIU Huimin, et al. Identifying up-to-date urban land-use patterns with visual and semantic features based on multisource geospatial data[J]. Sustainable Cities and Society, 2024, 101: 105184.

编辑推荐 0

Metrics

阅读次数

全文

100

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	14	0	0	86

来源	本网站	其他网站

次数	100	0
比例	100%	0%

摘要

135

最新录用	在线预览	正式出版

0	0	135

	来源	本网站

	次数	135
	比例	100%

方法	F₁值							Kappa系数
方法	交通	商业区	居民区	机构区	工地	水体	开放空间	Kappa系数
SO-CNN	0.684	0.310	0.760	0.528	0.238	0.649	0.555	0.514
DIHIO	0.666	0.490	0.748	0.377	0.541	0.732	0.537	0.544
RPF	0.706	0.375	0.766	0.636	0.323	0.619	0.554	0.518
本文方法	0.766	0.515	0.809	0.544	0.603	0.691	0.839	0.623

方法	F₁值								Kappa系数
方法	交通	商业区	居民区	机构区	工地		水体	开放空间	Kappa系数
SO-CNN	0.844	0.507	0.467	0.919	0.315	0.543	0.992	0.887	0.786
DIHIO	0.627	0.736	0.589	0.945	0.630	0.653	0.995	0.856	0.774
RPF	0.783	0.420	0.298	0.866	0.310	0.210	0.939	0.839	0.741
本文方法	0.708	0.810	0.948	0.849	0.790	0.912	0.899	0.932	0.827

方法	F₁值								Kappa系数
方法	交通	商业区	居民区	机构区	工地		水体	开放空间	Kappa系数
SO-CNN	0.482	0.530	0.519	0.843	0.668	0.459	0.801	0.825	0.652
DIHIO	0.397	0.414	0.480	0.842	0.647	0.557	0.695	0.787	0.612
RPF	0.410	0.426	0.464	0.835	0.579	0.366	0.640	0.822	0.613
本文方法	0.772	0.542	0.474	0.933	0.693	0.494	0.889	0.928	0.791

微调输入模态	Kappa系数
微调输入模态	北京数据集	洛杉矶数据集	伦敦数据集
光学	0.609	0.796	0.765
光学+OSM	0.623	0.827	0.791

面向城市功能区分类的光学遥感影像-OSM数据联合自监督学习方法

Self-supervised learning based urban functional zone classification by integrating optical remote sensing image-OSM data

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 32

相关文章 15

编辑推荐 0

Metrics

本文评价

[1]	陈占龙, 鲁谢春, 徐永洋. 基于图顶点深度聚类的建筑物合并方法[J]. 测绘学报, 2024, 53(4): 736-749.
[2]	薛志祥, 余旭初, 刘景正, 杨国鹏, 刘冰, 余岸竹, 周嘉男, 金上鸿. 面向多源异质遥感影像地物分类的自监督预训练方法[J]. 测绘学报, 2024, 53(3): 512-525.
[3]	曹帆之, 石添鑫, 韩开杨, 汪璞, 安玮. 多模态遥感图像模板匹配Log-Gabor滤波方法[J]. 测绘学报, 2024, 53(3): 526-536.
[4]	王密, 程昫, 潘俊, 皮英冬, 肖晶. 大模型赋能智能摄影测量：现状、挑战与前景[J]. 测绘学报, 2024, 53(10): 1955-1966.
[5]	燕琴, 顾海燕, 杨懿, 李海涛, 沈恒通, 刘世琦. 智能遥感大模型研究进展与发展方向[J]. 测绘学报, 2024, 53(10): 1967-1980.
[6]	张兵, 高连如, 李嘉鑫, 洪丹枫, 郑珂. 高/多光谱遥感图像超分辨率融合研究进展与展望[J]. 测绘学报, 2023, 52(7): 1074-1089.
[7]	余旭初, 刘冰, 薛志祥. 高光谱地物要素识别潜力分析与前景展望[J]. 测绘学报, 2023, 52(7): 1115-1125.
[8]	王超, 王帅, 陈晓, 李俊勇, 谢涛. 联合UNet++和多级差分模块的多源光学遥感影像对象级变化检测[J]. 测绘学报, 2023, 52(2): 283-296.
[9]	眭海刚, 刘畅, 干哲, 江政杰, 徐川. 多模态遥感图像匹配方法综述[J]. 测绘学报, 2022, 51(9): 1848-1861.
[10]	徐天河, 李耸, 王帅民, 江楠. 顾及气象数据的中国区域对流层延迟RBF神经网络优化模型[J]. 测绘学报, 2022, 51(8): 1690-1707.
[11]	李荣兴, 李国君, 冯甜甜, 沈强, 乔刚, 叶真, 夏梦莲. 基于光学遥感卫星影像的南极冰流速产品和方法研究综述[J]. 测绘学报, 2022, 51(6): 953-963.
[12]	陶超, 阴紫薇, 朱庆, 李海峰. 遥感影像智能解译:从监督学习到自监督学习[J]. 测绘学报, 2021, 50(8): 1122-1134.
[13]	李培, 姜刚, 马千里, 薛万峰, 杨伟华. 结合张量与互信息的混合模型多模态图像配准方法[J]. 测绘学报, 2021, 50(7): 916-929.
[14]	邓开元, 任超. 多光谱光学遥感影像水体提取模型[J]. 测绘学报, 2021, 50(10): 1370-1379.
[15]	陈占龙, 周路林, 禹文豪, 吴亮, 谢忠. 顾及兴趣点潜在上下文关系的城市功能区识别[J]. 测绘学报, 2020, 49(7): 907-920.