Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (3): 618-626    DOI: 10.11873/j.issn.1004-0323.2021.3.0618
遥感应用     
融合高分辨率遥感影像和POI数据的多特征潜在语义信息用于识别城市功能区
高子为1(),孙伟伟2(),程朋根1,杨刚2,孟祥超3
1.东华理工大学 测绘工程学院,江西 南昌 330013
2.宁波大学 地理与空间信息技术系,浙江 宁波 315211
3.宁波大学 信息科学与工程学院,浙江 宁波 315211
Identify Urban Functional Zones Using Multi Feature Latent Semantic Fused Information of High-spatial Resolution Remote Sensing Image and POI Data
Ziwei Gao1(),Weiwei Sun2(),Penggen Cheng1,Gang Yang2,Xiangchao Meng3
1.School of Surveying and Mapping Engineering,East China University of Technology,Nanchang,330013,China
2.Department of Geography and Spatial Information Techniques,Ningbo University,Ningbo 315211,China
3.Faculty of Electrical Engineering and Computer Science,Ningbo University,Ningbo 315211,China
 全文: PDF(5007 KB)   HTML
摘要:

准确识别和划分城市功能区对合理规划城市发展和解决城市问题具有重要作用。遥感影像拥有丰富的光谱纹理特征但难以表征建筑物的社会经济属性,而社交媒体数据等城市数据为城市研究与应用提供了丰富的数据资源,补充了遥感影像所缺失的建筑物内在特征。融合高分辨遥感影像和POI数据的多特征信息,利用嵌入主题模型挖掘其潜在语义信息识别城市功能区。以宁波市2个典型的城市商业区为研究区设计3个实验,验证该方法的效果和性能。研究结果表明:该方法能够取得85.67%和85.78%的分类精度,并准确识别出城市功能区。同时,光谱、纹理、几何和POI特征组合的多特征信息能够明显提升城市功能区的识别精度,并且嵌入主题模型能够更好地挖掘多特征的高层次潜在语义信息,效果明显优于pLSA、LDA和STM 3种主流模型。

关键词: 高分辨率遥感影像POI城市功能区识别多特征信息主题模型    
Abstract:

Accurate identification and division of urban functional zones play an important role in rational planning of urban development and solving urban problems. Remote sensing images have rich spectral texture features, but it is difficult to characterize the social and economic attributes of buildings, while urban data such as social media data provide rich data resources for urban research and application, and supplement the internal characteristics of buildings missing from remote sensing images. In this study, multi-feature information of high-resolution remote sensing image and POI data is integrated and embedded topic model is used to mine its potential semantic information to identify urban functional areas. Three experiments were designed with two typical urban business districts in Ningbo as the study area to verify the effect and performance of the research method. The results show that this method can achieve 85.67% and 85.78% classification accuracy, and can accurately identify urban functional zones. At the same time, the multi-feature information of spectral, texture, geometry and POI feature combination can significantly improve the identification accuracy of urban functional zones, and the embedded topic model can mine the high-level potential semantic information of multi-features better than the three mainstream topic models of pLSA, LDA and STM.

Key words: High spatial resolution remote sensing image    POI    Urban functional zones identification    Multi-feature information fusion    Topic model
收稿日期: 2020-09-15 出版日期: 2021-07-22
ZTFLH:  TP75  
基金资助: 国家重点研发计划项目(2017YFB0503704);国家自然科学基金项目(41861052);浙江省自然科学基金项目(LR1901D0001)
作者简介: 高子为(1996-),男,浙江宁波人,硕士研究生,主要从事城市遥感环境监测方面的研究。E?mail:nbgaoziwei@sina.cn|孙伟伟(1985-),男,河南巩义人,博士,教授,主要从事地理信息系统和遥感理论、方法及应用研究。E?mail:sunweiwei@nbu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
高子为
孙伟伟
程朋根
杨刚
孟祥超

引用本文:

高子为,孙伟伟,程朋根,杨刚,孟祥超. 融合高分辨率遥感影像和POI数据的多特征潜在语义信息用于识别城市功能区[J]. 遥感技术与应用, 2021, 36(3): 618-626.

Ziwei Gao,Weiwei Sun,Penggen Cheng,Gang Yang,Xiangchao Meng. Identify Urban Functional Zones Using Multi Feature Latent Semantic Fused Information of High-spatial Resolution Remote Sensing Image and POI Data. Remote Sensing Technology and Application, 2021, 36(3): 618-626.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.3.0618        http://www.rsta.ac.cn/CN/Y2021/V36/I3/618

图1  技术流程图
图2  研究区范围审图号:GS(2020)4632
类别ABGMRWS总计
研究区12304212551694398421 564
研究区21325258083167135251 147
表1  各功能区的真实样本信息一览表
类别ABGMRWS总计
总计1954762731624057461 564
A1442283201189
B11450441902490
G9524322102282
M273144503164
R27620432309389
W00100708
S2600502942
表2  研究区1的分类混淆矩阵
类别ABGMRWS总计
总计1255686492149134151 147
A891325412116
B17501321901543
G31355011073
M75182401100
R6293211712160
W030011310135
S340130920
表3  研究区2的分类混淆矩阵
研究区SpePOISpe+TexSpe+Tex+SURFSpe+Tex+SURF+GIST本文方法
1OA37.0262.8644.7064.7676.7085.67
Kappa24.6653.9432.3955.7969.7581.68
2OA39.2667.1349.7866.9676.9085.78
Kappa26.7258.0438.3157.3870.2480.03
表4  ETM模型中不同特征组合得到的分类精度对比 (%)
图3  研究区1不同特征组合的识别结果图
图4  研究区2不同特征组合的识别结果图
语义模型ABGMRWSOAKappa
pLSA60.0085.9980.0081.0767.4362.5045.2478.3271.46
LDA61.7489.5582.3582.8471.0775.0057.1481.274.68
STM65.2290.7492.9482.2572.2175.0064.2982.7476.73
ETM62.6193.1195.2985.2173.5887.5069.0585.6781.68
表5  4种语义模型用于识别研究区1中城市功能区的精度对比 (%)
语义模型ABGMRWSOAKappa
pLSA59.8589.1461.2589.1663.4790.372880.4772.19
LDA62.8890.6762.586.7567.0795.562880.9973.53
STM70.4592.1966.2590.3668.2692.593282.9177.86
ETM67.4295.4368.7598.870.0697.043685.7880.03
表6  4种语义模型用于识别研究区2中城市功能区的精度对比 (%)
1 Sun Weiwei,Yang Gang,Chen Chao, et al. Development Status and Literature Analysis of China’s Earth Observation Remote Sensing Satellites[J]. Journal of Remote Sensing,2020, 24(5):479-510.
1 孙伟伟,杨刚,陈超,等.中国地球观测遥感卫星发展现状及文献分析[J].遥感学报, 2020,24(5):479-510.]
2 Yang Zhaobin, Zhang Shuwen, Bu Kun, et al. Application of High Spatial Resolution Remote Sensing Image in Urban LUCC[J]. Journal of University of Chinese Academy of Sciences, 2016,33(3):289-297.
2 杨朝斌,张树文,卜坤,等.高分辨率遥感影像在城市LUCC中的应用[J].中国科学院大学学报,2016,33(3):289-297.]
3 Sun Danfeng, Yang Jihong, Liu Shunxi. Application of High-Spatial IKNOS Remote Sensing Images in Land Use Classification and Change Monitoring[J]. Journal of Agricultural Engineering, 2002,13(2):160-164.
3 孙丹峰,杨冀红,刘顺喜.高分辨率遥感卫星影像在土地利用分类及其变化监测的应用研究[J].农业工程学报,2002,13(2):160-164.]
4 Zhang X, Du S, Wang Q, et al. Multiscale Geoscene Segmentation for Extracting Urban Functional Zones from VHR Satellite Images[J]. Remote Sensing,2018,10(2):281. doi:10.3390/rs10020281.
doi: 10.3390/rs10020281
5 Tokarczyk P, Wegner J D, Walk S, et al. Features, Color Spaces, and Boosting: New Insights on Semantic Classification of Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing,2014,53(1):280-295. doi:10.1109/TGRS. 2014.2321423.
doi: 10.1109/TGRS. 2014.2321423
6 Zhong Y, Zhu Q, Zhang L. Scene Classification based on the Multifeature Fusion Probabilistic Topic Model for High Spatial Resolution Remote Sensing Imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015,53(11):6207–6222. doi:10.1109/TGRS.2015.2435801.
doi: 10.1109/TGRS.2015.2435801
7 Liu X, He J, Yao Y, et al. Classifying Urban Land Use by Integrating Remote Sensing and Social Media Data[J]. International Journal of Geographical Information Science, 2017, 31(8): 1675-1696. doi:10.1080/13658816.2017.13 24976.
doi: 10.1080/13658816.2017.13 24976
8 Gao Q, Fu J, Yu Y, et al. Identification of Urban Regions’ Functions in Chengdu, China, based on Vehicle Trajectory Data[J]. PLOS One,2019,14(4):e0215656. doi:10.1371/journal.pone.0215656.
doi: 10.1371/journal.pone.0215656
9 Tu W, Zhu T T, Xia J Z, et al. Portraying the Spatial Dynamics of Urban Vibrancy Using Multisource Urban Big Data[J]. Computer Environment and Urban Systems,2020,80: 101428. doi:10.1016/j.compenvurbsys.2019.101428.
doi: 10.1016/j.compenvurbsys.2019.101428
10 Tu W,Hu Z,Li L,et al.Portraying Urban Functional Zones by Coupling Remote Sensing Imagery and Human Sensing Data[J].Remote Sensing,2018,10(1):141. doi:10.3390/rs10010141.
doi: 10.3390/rs10010141
11 Zhu Y, Deng X, Newsam S. Fine-grained Land Use Classification at the City Scale Using Ground-level Images[J]. IEEE Transactions on Multimedia,2019,21(7):1825-1838. doi:10.1109/TMM.2019.2891999.
doi: 10.1109/TMM.2019.2891999
12 Yao Y, Li X, Liu X, et al. Sensing Spatial Distribution of Urban Land Use by Integrating Points-of-interest and Google Word2vec Model[J]. International Journal of Geographical Information Science,2017, 31(4):825–848. doi:10.1080/13658816.2016.1244608.]
doi: 10.1080/13658816.2016.1244608
13 Than K, Ho T B. Fully Sparse Topic Models[C]∥ Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Berlin, Heidelberg, 2012: 490-505. doi:10.1007/978-3-642-33460-3_37.
doi: 10.1007/978-3-642-33460-3_37
14 Zhang X, Du S, Zheng Z. Heuristic Sample Learning for Complex Urban Scenes: Application to Urban Functional-zone Mapping with VHR Images and POI Data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 161: 1-12. doi:10.1016/j.isprsjprs.2020.01.005.
doi: 10.1016/j.isprsjprs.2020.01.005
15 Dieng A B, Ruiz F J R, Blei D M. Topic Modeling in Embedding Spaces[J]. ArXiv Preprint ArXiv:1907.04907, 2019. doi:10.1162/tacl_a_00325.
doi: 10.1162/tacl_a_00325
16 Hu Yong, Liu Liangyun, Peter C, et al. Landsat Time-series Land Cover Mapping with Spectral Signature Extension Method[J]. Journal of Remote Sensing, 2015,19(4):639-656.
16 胡勇,刘良云,Peter C,等.光谱特征扩展的时间序列Landsat数据地表覆盖分类[J].遥感学报, 2015,19(4):639-656.]
17 Zhang Fafa, Li Weizhong, Lu Liuye,et al. Technologies of Extracting Land Utilization Information based on SVM Method with Multi-window Texture[J]. Journal of Remote Sensing, 2012,16(1):67-78.
17 张伐伐,李卫忠,卢柳叶,等,康乐SVM多窗口纹理土地利用信息提取技术[J].遥感学报,2012,16(1):67-78.]
18 Zhang B, Gao Y, Zhao S, et al. Local Derivative Pattern Versus Local Binary Pattern: Face Recognition with High-order Local Pattern Descriptor[J].IEEE transactions on Image Processing,2009,19(2):533-544.doi:10.1109/tip.2009.2035882.
doi: 10.1109/tip.2009.2035882
19 Bay H, Ess A, Tuytelaars T, et al. Speeded-up Robust Features (SURF)[J]. Computer Vision and Image Understanding,2008,110(3):346-359. doi:10.1016/j.cviu.2007.09.014.
doi: 10.1016/j.cviu.2007.09.014
20 Oliva A, Torralba A. Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope[J]. International Journal of Computer Vision,2001,42(3):145-175. doi: 10.1023/A:1011139631724.
doi: 10.1023/A:1011139631724
21 Jiang S, Alves A, Rodrigues F, et al. Mining Point-of-interest Data from Social Networks for Urban Land Use Classification and Disaggregation[J]. Computers, Environment and Urban Systems, 2015, 53: 36-46. doi:10.1016/j.compenvurbsys. 2014.12.001.
doi: 10.1016/j.compenvurbsys. 2014.12.001
22 Csurka G, Dance C, Fan L, et al. Visual Categorization with Bags of Keypoints[C]∥ Workshop on Statistical Learning in Computer Vision, ECCV. 2004, 1(1-22): 1-2. doi:10.1080/01621459.1949.10483312.
doi: 10.1080/01621459.1949.10483312
23 Jia Y, Ge Y, Ling F, et al. Urban Land Use Mapping by Combining Remote Sensing Imagery and Mobile Phone Positioning Data[J]. Remote Sensing, 2018, 10(3): 446. doi:10.3390/rs10030446.
doi: 10.3390/rs10030446
24 Bosch A, Zisserman A, Muñoz X. Scene Classification Via pLSA[C]∥ European Conference on Computer Vision. Sprin-ger, Berlin, Heidelberg, 2006:517-530. doi: 10.1007/11744085 _40.
doi: 10.1007/11744085 _40
25 Blei D M, Ng Andrew Y, Jordan M I. Latent Dirichlet Allocation[J]. Journal of Machine Learning Research,2003,3(33): 993-1022. doi:10.5555/9449 19.944937.
doi: 10.5555/9449 19.944937
[1] 陈敏,潘佳威,李江杰,徐璐,刘加敏,韩健,陈奕云. 结合VGGNet与Mask R-CNN的高分辨率遥感影像建设用地检测[J]. 遥感技术与应用, 2021, 36(2): 256-264.
[2] 康翔,潘剑君,朱燕香,白浩然,卢晓丽. 一种基于POI大数据的城市核心区识别方法[J]. 遥感技术与应用, 2021, 36(1): 237-246.
[3] 连喜红,祁元,王宏伟,张金龙,杨瑞. 基于面向对象的青海湖环湖区居民地信息自动化提取[J]. 遥感技术与应用, 2020, 35(4): 775-785.
[4] 王卓,闫浩文,禄小敏,冯天文,李亚珍. 一种改进U-Net的高分辨率遥感影像道路提取方法[J]. 遥感技术与应用, 2020, 35(4): 741-748.
[5] 费鲜芸,王婷,魏雪丽. 基于多尺度分割的遥感影像滨海湿地分类[J]. 遥感技术与应用, 2015, 30(2): 298-303.
[6] 张勇,谷正气,刘水长,罗伦,李程. 基于高分辨率遥感影像的城市群交通路网监测技术研究[J]. 遥感技术与应用, 2015, 30(1): 76-81.
[7] 钱家航,王金亮,马如彪,邓钰. 基于QuickBird影像城市道路特征语义信息提取[J]. 遥感技术与应用, 2014, 29(4): 653-659.
[8] 吴健生,林 倩,李卫锋,刘建政,彭 建. 基于特征选择的土地整理地物识别规则的动态提取[J]. 遥感技术与应用, 2013, 28(5): 799-806.
[9] 高利鹏,史文中,吕志勇,张华. 基于机载LiDAR和高分辨率遥感影像的城市道路网提取[J]. 遥感技术与应用, 2013, 28(4): 562-568.
[10] 刘 辉,谢天文. 基于PCA与HIS模型的高分辨率遥感影像阴影检测研究[J]. 遥感技术与应用, 2013, 28(1): 78-84.
[11] 张 扬,周子勇. 基于关联规则的面向对象高分辨率影像分类[J]. 遥感技术与应用, 2012, 27(3): 339-346.
[12] 周安发,周家香. 一种高分辨率遥感影像道路信息提取方法[J]. 遥感技术与应用, 2012, 27(1): 94-99.
[13] 张华,赵传燕,张勃,彭守璋. 高分辨率遥感影像GeoEye-1在黑河下游柽柳生物量估算中的应用 [J]. 遥感技术与应用, 2011, 26(6): 713-718.
[14] 张兴余, 刘勇, 许宝荣, 蒋志勇, 王晓燕, 王思维, 许民, 杨红卫. 乌兰布和沙漠高分辨率遥感影像梭梭林解译方法探讨[J]. 遥感技术与应用, 2010, 25(6): 828-835.
[15] 仇江啸, 王效科. 基于高分辨率遥感影像的面向对象城市土地覆被分类比较研究[J]. 遥感技术与应用, 2010, 25(5): 653-661.