Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (6): 1436-1445    DOI: 10.11873/j.issn.1004-0323.2021.6.1436
遥感应用     
基于Sentinel-2和全卷积网络的北京六环内高层建筑区提取与分析
朱金明1,2,李利伟2(),程钢1,高连如2,张兵2,3
1.河南理工大学 测绘与国土信息工程学院,河南 焦作 454000
2.中国科学院空天信息创新研究院 数字地球重点实验室,北京 100094
3.中国科学院大学,北京 100094
Detection and Analysis of High-rising Buildings within The sixth Ring Road of Beijing based on Sentinel-2 and Fully Convolutional Network
Jinming Zhu1,2,Liwei Li2(),Gang Cheng1,Lianru Gao2,Bing Zhang2,3
1.School of Surveying and Land Information Engineering,Henan Polytechnic University,Jiaozuo 454000,China
2.The Key Laboratory of Digital Earth Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China
3.University of Chinese Academy of Sciences,Beijing 100049,China
 全文: PDF(8002 KB)   HTML
摘要:

高层建筑区是我国城镇化进程的重要标志,具有重要的社会经济功能和独特的几何形态。应用全卷积网络和Sentinel-2多光谱数据,提取北京六环内高层建筑区,并结合环线、乡镇边界和轨道交通数据,对高层建筑区的空间分布和交通可达性进行分析。结果表明:实验提出的全卷积网络方法能够实现北京高层建筑区快速精确提取,总体精度90%以上;六环内高层建筑区总面积约为192 km2,其中,二环到四环之间分布最为密集且相对均匀,密度明显高于其他环带,二环内以及四环到五环之间相较次之,五环到六环之间密度最小;六环内街道乡镇的高层建筑区分布呈现明显片状聚集特点,密度最大的区域在崇文门外、东花市和建国门外等街道,其次是金融街街道、中关村街道和望京开发街道等区域,而靠近六环的街道乡镇和故宫附近街道的高层建筑区密度较小。轨道交通可达性与高层建筑区的空间分布存在明显相关性,交通可达性越差的区域,高层建筑区越少,地铁站点1 km范围内面积约为92.62 km2,而6 km外的面积只有2.04 km2。研究结果为北京城市建设和生态景观保护提供一个新的指标参考。

关键词: 高层建筑区Sentinel?2全卷积网络空间分析信息提取北京    
Abstract:

As an important symbol of China's urbanization process, high-rising buildings have important social and economic functions and unique geometric form. We proposed to use the fully convolutional network and Sentinel-2 multi-spectral data to extract high-rising buildings within the sixth Ring Road of Beijing, furthermore, we analyzed the spatial distribution and traffic accessibility of the high-rising buildings with the vector data of ring roads, township boundaries and rail transit stations. The results show that the proposed fully convolutional network based method can efficiently and effectively extract high-rising buildings from Sentinel-2 images in Beijing. The overall accuracy is above 90%. The total area of high-rising buildings within the sixth ring road is about 192 km2. The density of high-rising buildings between the second ring road and the fourth ring road is the densest and spatially uniform. Within the second ring and between the fourth and fifth rings is the secondary group. The density is the lowest between the fifth and sixth rings. High-rising buildings in the counties of the sixth Ring Road show obvious flake gathered characteristics, the largest area of density is in Chongwenmenwai Street, Donghuashi Street and Jianguomenwai Street et al., and they are followed by Financial street Street, Zhongguancun Street and Wangjing development Street et al.. The density of high-rising buildings in counties near the sixth Ring Road and The Forbidden City is rather low. The accessibility of rail transit has obvious spatial coupling with distribution of high-rising buildings. The lower the accessibility, the fewer high-rising buildings. The area within 1 km of subway station is about 92.62 km2, while the area at 6 km away is only 2.04 km2. Our results provide a new perspective for urban construction and ecological landscape protection in Beijing.

Key words: High-rising buildings    Sentinel-2    Fully convolutional network    Spatial analysis    Information extraction    Beijing
收稿日期: 2020-08-01 出版日期: 2022-01-26
ZTFLH:  P237  
基金资助: 国家自然科学基金项目(41971327);国家重点研发计划项目(2016YFB0501501);中国科学院战略先导项目(XDA19080304)
通讯作者: 李利伟     E-mail: lilw@radi.ac.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  
朱金明
李利伟
程钢
高连如
张兵

引用本文:

朱金明,李利伟,程钢,高连如,张兵. 基于Sentinel-2和全卷积网络的北京六环内高层建筑区提取与分析[J]. 遥感技术与应用, 2021, 36(6): 1436-1445.

Jinming Zhu,Liwei Li,Gang Cheng,Lianru Gao,Bing Zhang. Detection and Analysis of High-rising Buildings within The sixth Ring Road of Beijing based on Sentinel-2 and Fully Convolutional Network. Remote Sensing Technology and Application, 2021, 36(6): 1436-1445.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.6.1436        http://www.rsta.ac.cn/CN/Y2021/V36/I6/1436

图1  研究区真彩色影像及相关矢量数据(黄框为训练样本区,白框为结果验证区)
平均高度Sentinel-2影像Google影像社会功能
13~15 m普通住宅/别墅
16~18 m普通住宅
28~30 m高层住宅
48 m以上商服用地
表1  研究区内典型建筑区形状、功能和用途
图2  全卷积网络(FCN)结构
图3  部分训练样本二值标记切片数据(切片中白色为高层建筑区真值)
图4  高层建筑区提取技术流程
区域真值个数

正确率

/个数

虚警率 (个数)平均 正确率平均 虚警率
12696.15%(25)0.04%(1)93.03%0.06%
25492.59%(50)0.02%(1)
35488.89%(48)0.06%(3)
43390.90%(30)0.09%(3)
52396.65%(22)0.08%(2)
表2  精度验证结果
图5  验证样区示意(红色多边形为提取结果;黄色矩形为漏检区;绿色矩形为虚警)
图6  环线高层建筑区分布(红色图斑为高层建筑区)
图7  环带高层建筑区密度折线图
图8  街道乡镇高层建筑区密度图
图9  轨道交通可达性示意
图10  公里范围内高层建筑区面积折线图
1 Tang Yiqun, Yan Xuexin, Wang Jianxiu, et al. Model test study of influence of high-rise building on ground subsidence[J]. Journal of Tongji University(Natural Science Edition),2007,35(3):32-37.
1 唐益群, 严学新, 王建秀, 等. 高层建筑群对地面沉降影响的模型试验研究[J]. 同济大学学报(自然科学版), 2007,35(3):32-37.
2 Stewart I D, Oke T R. Local climate zones for urban temperature studies[J]. Bulletin of the American Meteorological Society, 2012, 93(12):1879-1900. DOI: 10.1175/BAMS-D-11-000191.
doi: 10.1175/BAMS-D-11-000191
3 Ge Yaning, Xu Xinliang, Li Jing, et al. Study on the influence of urban building density on the heat island effect in Beijing[J]. Journal of Geo-information Science,2016,18(12):1698-1706.
3 葛亚宁, 徐新良, 李静, 等. 北京城市建筑密度分布对热岛效应的影响研究[J]. 地球信息科学学报, 2016, 18(12):1698-1706.
4 Wang Jianhui. The investigation of airborne pollutant dispersion around high-rise residential buildings based on natural ventilation[D]. Chongqing: Chongqing University, 2011.
4 王建辉. 自然通风条件下高层居住建筑周围空气污染物扩散研究[D]. 重庆:重庆大学, 2011.
5 Miller R B, Small C. Cities from space: potential applications of remote sensing in urban environmental research and policy[J]. Environmental Science & Policy,2003,6:129-137. DOI:10.1016/S1462-9011(03)00002-9.
doi: 10.1016/S1462-9011(03)00002-9
6 Gong P, Li X, Wang J, et al. Annual maps of Global Artificial Impervious Area (GAIA) between 1985 and 2018[J]. Remote Sensing of Environment,2020,236,111510. DOI:10. 1016/j.rse.2019.111510.
doi: 10. 1016/j.rse.2019.111510
7 Guo Haitao, Liu Jishuang, Lu Jun. A integrative detection method of the areas containing high building based on correlative coefficient[J]. Journal of Geomatics Science and Technology,2009,26(2):125-127.
7 郭海涛, 刘继双, 卢俊. 基于相关系数的高层建筑物区域综合检测[J]. 测绘科学技术学报, 2009,26(2):125-127.
8 Li J, Roy D P. A global analysis of Sentinel-2A, Sentinel-2B and Landsat 8 data revisit intervals and implications for terrestrial monitoring[J]. Remote Sensing, 2017,9:902.
9 Yan Miao, Zhao Hongdong, Li Yuhai, et al. Multi-classification and recognition of hyperspectral remote sensing objects based on convolutional neural network[J]. Laser& Optoelectronics Progress,2019,56(2):191-198.
9 闫苗, 赵红东, 李宇海, 等. 基于卷积神经网络的高光谱遥感地物多分类识别[J]. 激光与光电子学进展,2019,56(2):191-198.
10 Song Tingqiang, Li Jixu, Zhang Xinye. Building recognition in high-resolution remote sensing image based on deep learning[J]. Computer Engineering and Applications,2020,56(8):26-34.
10 宋廷强,李继旭,张信耶.基于深度学习的高分辨率遥感图像建筑物识别[J]. 计算机工程与应用,2020,56(8):26-34.
11 Dong Zhipeng, Wang Mi, Li Deren, et al. Object detection in remote sensing imagery based on convolutional neural networks with suitable scale features[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(10):1285-1295.
11 董志鹏, 王密, 李德仁, 等. 遥感影像目标的尺度特征卷积神经网络识别法[J]. 测绘学报, 2019, 48(10): 1285-1295.
12 Xu X, Li W, Ran Q, et al. Multisource remote sensing data classification based on convolutional neural network[J]. IEEE Transactions on Geoscience & Remote Sensing,2018,56:937-949. DOI: 10.1109/TGRS.2017.2756851.
doi: 10.1109/TGRS.2017.2756851
13 Huang B, Zhao B, Song Y. Urban land-use mapping using a deep convolutional neural network with high spatial resolution multi-spectral remote sensing imagery[J]. Remote Sensing of Environment,2018,214,73-86. DOI:10.1016/j.rse.2018. 04.050.
doi: 10.1016/j.rse.2018. 04.050
14 Zhang L, Zhang L, Du B. Deep learning for remote sensing data: a technical tutorial on the state of the art[J]. IEEE Geoence & Remote Sensing Magazine,2016,4(2):22-40. DOI: 10.1109/MGRS.2016.2540798.
doi: 10.1109/MGRS.2016.2540798
15 Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(4):640-650. DOI:10.1109/CVPR.2015.7298965.
doi: 10.1109/CVPR.2015.7298965
16 Peng C, Li Y, Jiao L, et al. Densely based multi-scale and multi-modal fully convolutional networks for high-resolution remote sensing image semantic segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(8):2612-2626. DOI: 10.1109/JSTARS.2019.2906387.
doi: 10.1109/JSTARS.2019.2906387
17 Liang Zheyu, Wu Yanlan, Yang Hui, et al. Automatic water extraction from remote sensing images based on dense connected fully convolutional network[J]. Remote Sensing Information,2020,35(4):68-77.
17 梁泽毓, 吴艳兰, 杨辉, 等. 基于密集连接全卷积神经网络的遥感影像水体全自动提取方法[J]. 遥感信息,2020,35(4):68-77.
18 Pang Bo, Huang Zuoju, Wu Yanlan, et al. Extraction and mapping of impervious surface from high resolution remote sensing images based on improved fully convolutional network[J]. Remote Sensing Information,2020,35(4):47-55.
18 庞博, 黄祚继, 吴艳兰, 等. 基于改进全卷积神经网络的高分遥感影像不透水面提取制图[J]. 遥感信息,2020,35(4):47-55.
19 Zhang Yonghong, Xia Guanghao, Kai Xi, et al. Road extraction from multi-source high resolution remote sensing image based on fully convolutional neural network [J]. Journal of Computer Applications,2018,38(7):2070-2075.
19 张永宏, 夏广浩, 阚希, 等. 基于全卷积神经网络的多源高分辨率遥感道路提取[J]. 计算机应用,2018,38(7):2070-2075.
20 An Jie, Ma Jinwen. Automatic cloud segmentation based on the fully convolutional neural networks[J]. Journal of Signal Processing,2019,35(4):556-562.
20 安捷, 马尽文. 基于全卷积网络的遥感图像自动云检测[J]. 信号处理,2019,35(4): 556-562.
21 Li L, Yan Z, Shen Q, et al. Water body extraction from veryHigh spatial resolution remote sensing data based on fully convolutional networks[J].Remote Sensing,2019,11:1162.DOI:10.3390/rs11101162.
doi: 10.3390/rs11101162
22 Yan Zhi, Li Liwei, Cheng Gang. Extracting high-rise and low-rise building areas from Sentinel-2 Image using full convolutional network[J]. Bulletin of Surveying and Mapping, 2019(7):73-77.
22 闫智, 李利伟, 程钢. 利用全卷积网络提取Sentinel-2影像高低层建筑区[J]. 测绘通报,2019(7):73-77.
23 Li L, Zhu J, Gao L, et al. Detecting and analyzing the increase of high-rising buildings to monitor the dynamic of the Xiong’an new area[J]. Sustainability,2020,12:4355. DOI: 10.3390/su12114355.
doi: 10.3390/su12114355
24 Unified Standard for Civil Building Design: [S]. Beijing: China Architecture & Building Press, 2019.
24 民用建筑设计统一标准: [S]. 北京: 中国建筑工业出版社, 2019.
[1] 王曦,张怡雯. 基于Landsat影像的北京植被覆盖度变化趋势分析[J]. 遥感技术与应用, 2021, 36(6): 1388-1397.
[2] 梁爽,宫兆宁,赵文吉,关鸿亮,梁亚囡,陆丽,赵雪. 基于多季相Sentinel-2影像的白洋淀湿地信息提取[J]. 遥感技术与应用, 2021, 36(4): 777-790.
[3] 朱曼,张立福,王楠,林昱坤,张琳姗,王飒,刘华亮. 基于Sentinel-2的UNVI植被指数及性能对比研究[J]. 遥感技术与应用, 2021, 36(4): 936-947.
[4] 闫润州,李利伟,王涛,陈俊奇,赖健,张兵. 基于光谱聚类的高分影像复杂地块特征提取方法研究[J]. 遥感技术与应用, 2021, 36(3): 705-712.
[5] 徐光志,徐涵秋. Sentinel⁃2A MSI 和Landsat 8 OLI两种传感器多光谱信息的交互对比[J]. 遥感技术与应用, 2021, 36(1): 165-175.
[6] 唐倩迪,汪驰升,王永全,宿瑞博,江锦成,崔红星. 志愿者民航客机夜光遥感光污染监测初步研究[J]. 遥感技术与应用, 2020, 35(6): 1360-1367.
[7] 王一帆,徐涵秋. 基于客观阈值与随机森林Gini指标的水体遥感指数对比[J]. 遥感技术与应用, 2020, 35(5): 1089-1098.
[8] 夏炎,黄亮,王枭轩,陈朋弟. 基于无人机影像的烟草精细提取[J]. 遥感技术与应用, 2020, 35(5): 1158-1166.
[9] 李萌,年雁云,边瑞,白艳萍,马金辉. 基于多源遥感影像的青海云杉和祁连圆柏分类[J]. 遥感技术与应用, 2020, 35(4): 855-863.
[10] 徐玉雯,张浩,陈正超,景海涛. 基于深蓝算法的Sentinel-2数据气溶胶光学厚度反演[J]. 遥感技术与应用, 2020, 35(2): 372-380.
[11] 胡云锋,商令杰,张千力,王召海. 基于GEE平台的1990年以来北京市土地变化格局及驱动机制分析[J]. 遥感技术与应用, 2018, 33(4): 573-583.
[12] 马真东,摆玉龙. 基于地理处理服务的地下水脆弱性评价研究[J]. 遥感技术与应用, 2018, 33(4): 759-765.
[13] 孟庆岩,孙云晓,张佳晖,等. 基于多源遥感的建筑区绿化垂直分布特征与空间配置分析——以匈牙利塞克什白堡市为例[J]. 遥感技术与应用, 2018, 33(2): 370-376.
[14] 王雪梅,马明国. 关联DMSP-OLS灯光数据的全球发文量态势分析[J]. 遥感技术与应用, 2017, 32(6): 1093-1099.
[15] 周在明,杨燕明,陈本清. 基于无人机影像的滩涂入侵种互花米草植被信息提取与覆盖度研究[J]. 遥感技术与应用, 2017, 32(4): 714-720.