Hierarchical Spatial Recognition Method for Urban Villages by Integrating Multi-source Geospatial Data
-
摘要: 城中村的精细空间分布是城市规划与城市更新的重要参考。由于城中村具有语义高级和遥感影像特征辨识度不足的特点，使用传统的场景识别方法难以从高密度城市中获得精度良好的城中村精细空间分布。针对城中村的精细识别问题，提出了一种新颖的融合遥感影像和社会感知的层次化识别方法。该方法在特征上融合了遥感图像和社会感知数据的优点，其层次化结构同时考虑了大范围的上下文信息和小范围的局部信息，为在精细尺度全面理解城中村提供了一个新思路。基于该方法对深圳市的城中村进行了空间识别，获得了2.5 m空间分辨率的精细城中村分布。精度验证表明，该结果的总体精度和Kappa系数分别达到98.68%和0.807，说明该方法具有优秀的表现。此外，还通过对照实验分别证明了层次化识别框架、融合遥感影像和社会感知数据的增益效果。结果表明，层次化框架和多源空间数据都能有效提高城中村识别方法的精度。Abstract:Objectives The fine spatial distribution of urban villages is important for urban planning and urban renewal. However, since urban villages are high-level semantic geo-objects and have obscure remote sensing characteristics, it is difficult to obtain fine spatial distribution with good precision from high-density cities using traditional methods.Methods We propose a novel hierarchical recognition method for urban villages that fuses remote sensing images and social sensing data to finely recognize the urban villages. The method combines the advantages of remote sensing images and social perception data in features. Large- and small-scale information are both considered into the process by using the hierarchical framework.Results The method provides a new idea for a comprehensive understanding of urban villages at a fine scale. A case study has been implemented in Shenzhen. An urban village distribution with a spatial resolution of 2.5 m is obtained. The accuracy assessment shows that the overall accuracy and Kappa coefficient reach 98.68% and 0.807, respectively, indicating the excellent performance of the method. In addition, the gain effects of the hierarchical framework and the fusion of remote sensing images and social perception data are demonstrated, respectively.Conclusions The results show that both the hierarchical framework and the multi-source spatial data are effective in improving the accuracy of the urban village recognition method.
-
-
![]()
图 2 基于多源空间数据的城中村层次化识别方法流程图
Figure 2. Flowchart of Hierarchical Spatial Recognition Method by Integrating Multi-source Geospatial Data
表 1 样本设置
Table 1 Configuration of Samples
步骤 城中村 非城中村 训练对象数量 测试对象数量 训练对象数量 测试对象数量 粗识别 50 211 50 600 精细识别 6 194 800 850 5 879 20 841 992 
下载: 导出CSV
表 2 基于多源空间特征的随机森林方法与基准方法的精度统计
Table 2 Accuracy Statistics of the Results Obtained by the Hierarchical Spatial Recognition Method Integrated Multi-source Geospatial Data and Baseline Methods
步骤 方法 Kappa系数 总体精度/% 粗识别 基于常用遥感特征的随机森林模型 0.784 93.43 基于多源空间特征的SVM模型 0.841 93.96 本文方法 0.858 94.82 精细识别 基于常用遥感特征的随机森林模型 0.730 98.21 基于多源空间特征的SVM模型 0.787 98.51 本文方法 0.807 98.68
下载: 导出CSV
表 3 使用层次化识别框架与否的识别精度统计
Table 3 Accuracy Statistics of the Methods Using Hierarchical Identification Framework or Not
指标 本文方法 通用像素级分类 Kappa系数 0.807 0.685 总体精度/% 98.68 97.46 漏判误差 0.210 0.147 错判误差 0.161 0.410
下载: 导出CSV
表 4 不同输入特征的识别精度统计
Table 4 Recognition Accuracy Statistics of the Results Produced by Different Input Features
步骤 指标 遥感图像特征 人类活动特征 多源空间特征 粗识别 Kappa系数 0.814 0.765 0.858 总体精度/% 93.22 90.63 94.83 精细识别 Kappa系数 0.769 0.593 0.807 总体精度/% 98.45 96.85 98.68
下载: 导出CSV
-
[1] 赵静, 薛德升, 闫小培. 国外非正规聚落的改造模式与借鉴[J]. 规划师, 2009, 25(1): 80-84. https://www.cnki.com.cn/Article/CJFDTOTAL-GHSI200901026.htm Zhao Jing, Xue Desheng, Yan Xiaopei. The Models of Informal Settlements Upgrading Abroad and Implications for China[J]. Planners, 2009, 25(1): 80-84 https://www.cnki.com.cn/Article/CJFDTOTAL-GHSI200901026.htm
[2] Gallaher C M, Kerr J M, Njenga M, et al. Urban Agriculture, Social Capital, and Food Security in the Kibera Slums of Nairobi, Kenya[J]. Agriculture and Human Values, 2013, 30(3): 389-404. doi: 10.1007/s10460-013-9425-y
[3] Li Z G, Wu F L. Residential Satisfaction in China's Informal Settlements: A Case Study of Beijing, Shanghai, and Guangzhou[J]. Urban Geography, 2013, 34(7): 923-949. doi: 10.1080/02723638.2013.778694
[4] 李培林. 巨变: 村落的终结: 都市里的村庄研究[J]. 中国社会科学, 2002(1): 168-179. https://www.cnki.com.cn/Article/CJFDTOTAL-ZSHK200201015.htm Li Peilin. Tremendous Changes: The End of Villages: A Study of Villages in the Center of Guangzhou City[J]. Social Sciences in China, 2002(1): 168-179 https://www.cnki.com.cn/Article/CJFDTOTAL-ZSHK200201015.htm
[5] 仝德, 冯长春. 国内外城中村研究进展及展望[J]. 人文地理, 2009, 24(6): 29-35. doi: 10.13959/j.issn.1003-2398.2009.06.009 Tong De, Feng Changchun. Review and Progress of the Research on Urban Villages[J]. Human Geography, 2009, 24(6): 29-35 doi: 10.13959/j.issn.1003-2398.2009.06.009
[6] 魏立华, 闫小培. "城中村": 存续前提下的转型: 兼论"城中村"改造的可行性模式[J]. 城市规划, 2005, 29(7): 9-13. doi: 10.3321/j.issn:1002-1329.2005.07.002 Wei Lihua, Yan Xiaopei. Transformation of "Urban Village" and Feasible Mode[J]. City Planning Review, 2005, 29(7): 9-13 doi: 10.3321/j.issn:1002-1329.2005.07.002
[7] Huang X, Liu H, Zhang L. Spatiotemporal Detection and Analysis of Urban Villages in Mega City Regions of China Using High-Resolution Remotely Sensed Imagery [J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(7): 3639-3657. doi: 10.1109/TGRS.2014.2380779
[8] Mahabir R, Croitoru A, Crooks A, et al. A Critical Review of High and very High-Resolution Remote Sensing Approaches for Detecting and Mapping Slums: Trends, Challenges and Emerging Opportunities[J]. Urban Science, 2018, 2(1): 8. doi: 10.3390/urbansci2010008
[9] Kuffer M, Pfeffer K, Sliuzas R. Slums from Space: 15 Years of Slum Mapping Using Remote Sensing[J]. Remote Sensing, 2016, 8(6): 455. doi: 10.3390/rs8060455
[10] Liu Y, Liu X, Gao S, et al. Social Sensing: A New Approach to Understanding our Socioeconomic Environments[J]. Annals of the Association of American Geographers, 2015, 105(3): 512-530. doi: 10.1080/00045608.2015.1018773
[11] 刘瑜, 詹朝晖, 朱递, 等. 集成多源地理大数据感知城市空间分异格局[J]. 武汉大学学报(信息科学版), 2018, 43(3): 327-335. doi: 10.13203/j.whugis20170383 Liu Yu, Zhan Zhaohui, Zhu Di, et al. Incorporating Multi-source Big Geo-Data to Sense Spatial Heterogeneity Patterns in an Urban Space[J]. Geomatics and Information Science of Wuhan University, 2018, 43(3): 327-335 doi: 10.13203/j.whugis20170383
[12] 涂伟, 曹劲舟, 高琦丽, 等. 融合多源时空大数据感知城市动态[J]. 武汉大学学报(信息科学版), 2020, 45(12): 1875-1883. doi: 10.13203/j.whugis20200535 Tu Wei, Cao Jinzhou, Gao Qili, et al. Sensing Urban Dynamics by Fusing Multi-sourced Spatiotemporal Big Data[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1875-1883 doi: 10.13203/j.whugis20200535
[13] Cao R, Tu W, Yang C, 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. doi: 10.1016/j.isprsjprs.2020.02.014
[14] Chen Y, Liu X, Gao W, et al. Emerging Social Media Data on Measuring Urban Park Use[J]. Urban Forestry & Urban Greening, 2018, 31: 130-141.
[15] Zhang X, Du S, Wang Q. Hierarchical Semantic Cognition for Urban Functional Zones with VHR Satellite Images and POI Data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 132: 170-184. doi: 10.1016/j.isprsjprs.2017.09.007
[16] Mou X, Cai F, Zhang X, et al. Urban Function Identification Based on POI and Taxi Trajectory Data[C]// The 3rd International Conference on Big Data Research, Cergy-Pontoise, France, 2019.
[17] Chen Y, Liu X, Li X, et al. Delineating Urban Functional Areas with Building-Level Social Media Data: A Dynamic Time Warping (DTW) Distance Based k-Medoids Method[J]. Landscape and Urban Planning, 2017, 160: 48-60. doi: 10.1016/j.landurbplan.2016.12.001
[18] Mao F, Ji M, Liu T. Mining Spatiotemporal Patterns of Urban Dwellers from Taxi Trajectory Data[J]. Frontiers of Earth Science, 2016, 10(2): 205-221. doi: 10.1007/s11707-015-0525-4
[19] Chaib S, Liu H, Gu Y, et al. Deep Feature Fusion for VHR Remote Sensing Scene Classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(8): 4775-4784. doi: 10.1109/TGRS.2017.2700322
[20] Belgiu M, Csillik O. Sentinel-2 Cropland Mapping Using Pixel-Based and Object-Based Time-Weighted Dynamic Time Warping Analysis[J]. Remote Sensing of Environment, 2018, 204: 509-523. doi: 10.1016/j.rse.2017.10.005
[21] Farabet C, Couprie C, Najman L, et al. Learning Hierarchical Features for Scene Labeling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1915-1929. doi: 10.1109/TPAMI.2012.231
[22] Li Y, Huang X, Liu H. Unsupervised Deep Feature Learning for Urban Village Detection from High-Resolution Remote Sensing Images[J]. Photogrammetric Engineering & Remote Sensing, 2017, 83(8): 567-579.
[23] Fang L, Li S, Kang X, et al. Spectral-Spatial Classification of Hyperspectral Images with a Superpixel-Based Discriminative Sparse Model[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(8): 4186-4201. doi: 10.1109/TGRS.2015.2392755
[24] Tu W, Zhang Y, Li Q, et al. Scale Effect on Fusing Remote Sensing and Human Sensing to Portray Urban Functions[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18(1): 38-42. doi: 10.1109/LGRS.2020.2965247
[25] 李双成, 蔡运龙. 地理尺度转换若干问题的初步探讨[J]. 地理研究, 2005, 24(1): 11-18. https://www.cnki.com.cn/Article/CJFDTOTAL-DLYJ200501001.htm Li Shuangcheng, Cai Yunlong. Some Scaling Issues of Geography[J]. Geographical Research, 2005, 24(1): 11-18 https://www.cnki.com.cn/Article/CJFDTOTAL-DLYJ200501001.htm
[26] 张秀红, 陈迪, 刘纪平, 等. 结构化居民地群的多层次识别方法[J]. 武汉大学学报(信息科学版), 2018, 43(8): 1144-1151. doi: 10.13203/j.whugis20160239 Zhang Xiuhong, Chen Di, Liu Jiping, et al. A Multilevel Identification Approach to Structured Building Clusters[J]. Geomatics and Information Science of Wuhan University, 2018, 43(8): 1144-1151 doi: 10.13203/j.whugis20160239
[27] 姚尧, 张亚涛, 关庆锋, 等. 使用时序出租车轨迹识别多层次城市功能结构[J]. 武汉大学学报(信息科学版), 2019, 44(6): 875-884. doi: 10.13203/j.whugis20170111 Yao Yao, Zhang Yatao, Guan Qingfeng, et al. Sensing Multi-level Urban Functional Structures by Using Time Series Taxi Trajectory Data[J]. Geomatics and Information Science of Wuhan University, 2019, 44(6): 875-884 doi: 10.13203/j.whugis20170111
[28] 朱国宾. 面向多分辨率层次结构的遥感影像分析方法[J]. 武汉大学学报(信息科学版), 2003, 28(3): 315-320. http://ch.whu.edu.cn/article/id/4822 Zhu Guobin. Remote Sensing Image Analysis Based on Hierarchical Multi-resolution Structures[J]. Geomatics and Information Science of Wuhan University, 2003, 28(3): 315-320 http://ch.whu.edu.cn/article/id/4822
[29] Li Q, Tu W, Zhuo L. Reliable Rescue Routing Optimization for Urban Emergency Logistics Under Travel Time Uncertainty[J]. ISPRS International Journal of Geo-Information, 2018, 7(2): 77.
[30] 谷岩岩, 焦利民, 董婷, 等. 基于多源数据的城市功能区识别及相互作用分析[J]. 武汉大学学报(信息科学版), 2018, 43(7): 1113-1121. doi: 10.13203/j.whugis20160192 Gu Yanyan, Jiao Limin, Dong Ting, et al. Spatial Distribution and Interaction Analysis of Urban Functional Areas Based on Multi-source Data[J]. Geomatics and Information Science of Wuhan University, 2018, 43(7): 1113-1121 doi: 10.13203/j.whugis20160192
[31] Chen Y, Chen Q, Jing C. Multi-resolution Segmentation Parameters Optimization and Evaluation for VHR Remote Sensing Image Based on mean NSQI and Discrepancy Measure[J]. Journal of Spatial Science, 2021, 66(2): 253-278.
[32] Singh S, Singh A K. Correlation-Based Feature Subset Selection Technique for Web Spam Classification[J]. International Journal of Web Engineering and Technology, 2018, 13(4): 363–379.
[33] Bunker R P, Thabtah F. A Machine Learning Framework for Sport Result Prediction[J]. Applied Computing and Informatics, 2019, 15(1): 27-33.
[34] Delgado M F, Cernadas E, Barro S, et al. Do We Need Hundreds of Classifiers to Solve Real World Classification Problems?[J]. Journal of Machine Learning Research, 2014, 15(1): 3133-3181.
[35] Gavankar N, Ghosh S. Automatic Building Footprint Extraction from High-Resolution Satellite Image Using Mathematical Morphology [J]. European Journal of Remote Sensing, 2018, 51(1): 182-193.
计量
- 文章访问数: 624
- HTML全文浏览量: 126
- PDF下载量: 155
