Urban land use classification based on remote sensing and multi-source geographic data
-
摘要: 城市土地利用信息体现了城市的功能及结构,开展城市土地利用分类研究对于城市可持续发展具有重要指导意义。以哈尔滨市主城区为研究区,综合应用Sentinel-2A遥感影像、OpenStreetMap(OSM)数据、兴趣点(point of interest,POI)数据和珞珈一号夜间灯光数据等多源地理数据,采用面向对象和随机森林算法对哈尔滨城市土地利用进行分类。结果表明: 一级地类总体精度为86.0%,Kappa系数为0.75; 二级地类总体精度为73.9%,Kappa系数为0.69; POI数据可以显著提高住宅用地、工矿仓储用地和教育用地分类精度,夜间灯光数据能有效提高商务办公用地及商业用地分类精度。说明遥感影像与多源地理数据结合对城市土地利用分类有效。Abstract: Urban land use (ULU) reflects urban functions and structures, and the study of ULU classification can provide guidance for the sustainable development of cities. This study conducted the ULU classification of the main urban area of Harbin City using the object-oriented and random forest methods by integrating multi-source geospatial data including Sentinel-2A remote sensing images, OpenStreetMap (OSM) data, point of interest (POI) data, and nighttime light data from the Luojia-1 satellite. The results are as follows. The overall accuracy of the first-level land use type was 86.0%, with a Kappa coefficient of 0.75. The overall accuracy of the second-level land use types was 73.9%, with a Kappa coefficient of 0.69. The introduction of POI data can significantly improve the classification accuracy of residential land, industrial and mining storage land, and educational land. Meanwhile, night light data can effectively improve the classification accuracy of commercial office land and business land. This study shows that the combination of remote sensing images with multi-source geographic data is effective for ULU classification.
-
Key words:
- random forest /
- multi-scale segmentation /
- multi-source data /
- urban land use classification /
- Harbin
-
-
[1] doi: 10.6046/gtzyyg.2014.04.09. [19] Yang Y, Xu L, Yan P L. Urban land use/cover remote sensing classification based on random forest under conditional random field framework[J]. Remote Sensing for Land and Resources, 2014, 26(4):51-55.doi: 10.6046/gtzyyg.2014.04.09. [20] 薛冰, 肖骁, 李京忠. 基于兴趣点(POI)大数据的东北城市空间结构分析[J]. 地理科学, 2020, 40(5):691-700. [20] Xue B, Xiao X, Li J Z. Spatial structure analysis of northeast cities based on big data of point of interest (POI)[J]. Geographical Sciences, 2020, 40(5):691-700.[21] 李欣. 基于POI要素空间聚集特征的城市多中心结构识别——以郑州市为例[J]. 北京大学学报(自然科学版), 2020, 56(4):692-702.[21] Li X. Urban multi-center structure recognition based on the spatial aggregation characteristics of POI elements:Taking Zhengzhou as an example[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2020, 56(4):692-702.[22] Brovelli M, Zamboni G. A new method for the assessment of spatial accuracy and completeness of OpenStreetMap building footprints[J]. ISPRS International Journal of Geo-Information, 2018, 7(8):289. [23] 郑纪玲. 数据清洗在构建POI数据仓库中的研究与应用[D]. 北京:中国矿业大学(北京),2016.[23] Zheng J L. Research and application of data cleaning in the construction of POI data warehouse[D]. Beijing:China University of Mining and Technology(Beijing),2016.[24] 陈颖彪, 郑子豪, 吴志峰, 等. 夜间灯光遥感数据应用综述和展望[J]. 地理科学进展, 2019, 38(2):205-223. [24] Chen Y B, Zheng Z H, Wu Z F, et al. Summary and prospect of the application of nighttime light remote sensing data[J]. Progress in Geography, 2019, 38(2):205-223.[25] 李黔湘, 郑晗, 张过, 等. 基于夜间灯光影像的珞珈一号指数分析[J]. 测绘地理信息, 2020, 45(3):8-15.[25] Li Q X, Zheng H, Zhang G, et al. Analysis of Luojia-1 index based on nighttime light image[J]. Geoinformation of Surveying and Mapping, 2020, 45(3):8-15.[26] 林先成, 李永树. 成都平原高分辨率遥感影像分割尺度研究[J]. 自然资源遥感, 2010, 22(2):7-11.doi: 10.6046/gtzyyg.2010.02.02. [26] Lin X C, Li Y S. Research on the segmentation scale of high-resolution remote sensing image of Chengdu Plain[J]. Remote Sensing for Land and Resources, 2010, 22(2):7-11.doi: 10.6046/gtzyyg.2010.02.02. [27] 王露, 刘庆元. 高分辨率遥感影像多尺度分割中最优尺度选取方法综述[J]. 测绘与空间地理信息, 2015, 38(3):166-169.[27] Wang L, Liu Q Y. A review of optimal scale selection methods in multi-scale segmentation of high-resolution remote sensing images[J]. Surveying and Spatial Information, 2015, 38(3):166-169.[28] 黄欢欢, 黄万里. 基于面向对象分类方法的城市用地类型提取[J]. 福建师范大学学报(自然科学版), 2014, 30(6):96-102.[28] Huang H H, Huang W L. Urban land type extraction based on object-oriented classification method[J]. Journal of Fujian Normal University (Natural Science Edition), 2014, 30(6):96-102.[29] Woodcock C, Eand Strahler A H. The factor of scale in remote sensing[J]. Remote Sensing of Environment, 1987, 21(3):311-332. [30] 李治, 杨晓梅, 孟樊, 等. 物候特征辅助下的随机森林宏观尺度土地覆盖分类方法研究[J]. 遥感信息, 2013, 28(6):48-55.[30] Li Z, Yang X M, Meng F, et al. Random forest macro-scale land cover classification method aided by phenological characteristics[J]. Remote Sensing Information, 2013, 28(6):48-55.
-
计量
- 文章访问数: 1034
- PDF下载数: 55
- 施引文献: 0
下载: