基于遥感解译的中国农房空间分布特征分析

doi:10.11821/dlxb202204005

地理学报 ›› 2022, Vol. 77 ›› Issue (4): 835-851.doi: 10.11821/dlxb202204005

基于遥感解译的中国农房空间分布特征分析

李郇¹(), 许伟攀¹, 黄耀福¹, 陈浩辉², 秦小珍¹, 李颖³, 邓明亮³, 姜俊浩¹, 秦雅雯¹

1. 中山大学地理科学与规划学院中山大学中国区域协调发展与乡村建设研究院,广州 510275
2. 澳大利亚联邦科学与工业研究组织,墨尔本 3008
3. 奥格科技股份有限公司,广州 510663

收稿日期:2021-08-23 修回日期:2022-02-28 出版日期:2022-04-25 发布日期:2022-06-20
作者简介:李郇(1964-), 男, 江西南昌人, 教授, 博导, 研究方向为经济地理、城市规划和乡村建设。E-mail: lixun@mail.sysu.edu.cn
基金资助:
国家社会科学基金项目(21AZD034);国家自然科学基金项目(41971157)

Spatial distribution of rural building in China: Remote sensing interpretation and density analysis

LI Xun¹(), XU Weipan¹, HUANG Yaofu¹, CHEN Haohui², QIN Xiaozhen¹, LI Ying³, DENG Mingliang³, JIANG Junhao¹, QIN Yawen¹

1. China Regional Coordinated Development and Rural Construction Institute, School of Geography and Planning, Sun Yat-sen University, Guangzhou, 510275, China
2. Commonwealth Scientific and Industrial Research Organisation, Melbourne 3008, Australia
3. Augur Intelligence Technology Co., Ltd, Guangzhou, 510663, China

Received:2021-08-23 Revised:2022-02-28 Published:2022-04-25 Online:2022-06-20
Supported by:
National Social Science Foundation of China, No.21AZD034(21AZD034);National Natural Science Foundation of China, No.41971157](41971157)

摘要/Abstract

摘要：

中国农房分布研究是乡村振兴的基础性工作之一。本文利用Mask R-CNN深度学习框架,采用亚米级遥感影像,基于中国各省农房的人文地理特征,分省训练出适用于本地的农房遥感解译模型,共识别1484个县的1.54亿栋农房,总建筑面积达298.2亿m²,创建出以单体农房为基础的多尺度中国农房数据库。本文分别以县域、镇域和聚落为单元进行农房密度分析：县域单元的农房密度呈现“东密西疏”的分布特征,与胡焕庸线揭示的人口分布格局相符;镇域单元的农房密度沿三大地形阶梯自西向东递增,分布从集中走向平均,与农业区划的农业生产力、地形地貌特征高度耦合;聚落单元的农房分布则呈现“南密北疏”特征形态,与气候条件、地形地貌、人均耕地等相关联。中国农房数据库的建设将为“可计算的”乡村研究奠定基础。

关键词: 农房, 遥感解译, 密度, 分布, 可计算, 中国

Abstract:

The research on the distribution of rural buildings is one of the essential works of rural revitalization in China. Adopting Mask R-CNN deep learning framework and collecting sub-meter remote sensing image, this research successfully trains remote sensing interpretation models suitable for local rural buildings based on the human geographical characteristics in each province. A multi-scale database of Chinese rural building based on single rural building has been created, including 154 million agricultural houses in 1484 counties with a total construction area of 29.82 billion square meters. Based on the database, this paper analyzes the distribution characteristics of rural buildings at the county, town and settlement scales. At the county scale, the density of rural buildings showed a distribution pattern of 'dense in the east and sparse in the west', consistent with the population distribution pattern revealed by Hu Huanyong Line. At the town scale, the density of rural buildings increases from west to east with the descent of three terrain steps, and the spatial distribution tends to be balanced, corresponding to the agricultural productivities and topography in the agricultural zones. At the settlement scale, the distribution of rural buildings shows the pattern of 'dense in the south and sparse in the north', consistent to the climate condition, topography and arable land per capita. The construction of China's rural building spatial database could lay a solid foundation for the "computational" rural research in the future.

Key words: rural housing, remote sensing interpretation, density, distribution, computation, China

李郇, 许伟攀, 黄耀福, 陈浩辉, 秦小珍, 李颖, 邓明亮, 姜俊浩, 秦雅雯. 基于遥感解译的中国农房空间分布特征分析[J]. 地理学报, 2022, 77(4): 835-851.

LI Xun, XU Weipan, HUANG Yaofu, CHEN Haohui, QIN Xiaozhen, LI Ying, DENG Mingliang, JIANG Junhao, QIN Yawen. Spatial distribution of rural building in China: Remote sensing interpretation and density analysis[J]. Acta Geographica Sinica, 2022, 77(4): 835-851.

图/表 10

图1

图2

图3

图4

图5

图6

表1

图7

图8

图9

参考文献 44

[1]	Sun Tong, Xiao Xiao. Analysis of regional differences and influencing factors of rural housing conditions in China. China Market, 2016(20):36-39, 57.
	[ 孙童, 肖霄. 中国农村住房状况的区域差异与影响因素分析. 中国市场, 2016(20):36-39, 57.]
[2]	Wang Ying, Wang Jing'ai, Yang Chunyan, et al. Research on the rural residents housings in China. Economic Geography, 2006, 26(Suppl.1):198-200.
	[ 王瑛, 王静爱, 杨春燕, 等. 中国农村居民住房现状分析. 经济地理, 2006, 26(S1):198-200.]
[3]	Yi Chengdong. An analysis of inter-provincial differences in housing conditions of rural families in China. Rural Economy, 2006(12):103-106.
	[ 易成栋. 中国农村家庭住房状况的省际差异分析. 农村经济, 2006(12):103-106.]
[4]	Gao Xiaolu, Jin Fengjun, Ji Jue. Establishment of a county-level housing structure database in China. Geographical Research, 2011, 30(12):2127-2138.
	[ 高晓路, 金凤君, 季珏. 基于尺度收缩方法的中国县级尺度房屋结构数据推算. 地理研究, 2011, 30(12):2127-2138.]
[5]	Gao Xiaolu, Ji Jue, Jin Fengjun, et al. Seismic vulnerability of rural housing and regional anti-disaster strategies in China. Acta Geographica Sinica, 2012, 67(2):211-220. doi: 10.11821/xb201202007
	[ 高晓路, 季珏, 金凤君, 等. 中国农村房屋震灾脆弱性评估及其成因分析. 地理学报, 2012, 67(2):211-220.] doi: 10.11821/xb201202007
[6]	Li Fangyi, Gao Xiaolu, Wang Yingjie. Regional differentiation of housing structure and its influencing factors in rural areas of China. Progress in Geography, 2011, 30(12):1555-1563.
	[ 李方一, 高晓路, 王英杰. 中国农村地区住房结构的区域差异及其影响因素. 地理科学进展, 2011, 30(12):1555-1563.]
[7]	Xu Xiaoren, Xu Yong. Provision and regional difference of residential housing indoor facilities in China. Progress in Geography, 2016, 35(2):173-183. doi: 10.18306/dlkxjz.2016.02.004
	[ 徐小任, 徐勇. 中国居民住房内生活设施配置及区域差异. 地理科学进展, 2016, 35(2):173-183.] doi: 10.18306/dlkxjz.2016.02.004
[8]	Ye Liu. Temporal and spatial analysis of county differences in residential housing quality in China. The World of Survey and Research, 2016(1):49-53.
	[ 叶柳. 我国居民住房质量的县域差异时空分析. 调研世界, 2016(1):49-53.]
[9]	Hu Huanyong. Population distribution in China with statistical table and density map. Acta Geographica Sinica, 1935, 2(2):33-74. doi: 10.11821/xb193502002
	[ 胡焕庸. 中国人口之分布: 附统计表与密度图. 地理学报, 1935, 2(2):33-74.] doi: 10.11821/xb193502002
[10]	Yang Bin, Cheng Ziyang. Research and analysis on town-level housing structure database in Shanxi based on down scaling. Shanxi Science and Technology, 2019, 34(6):122-127.
	[ 杨斌, 程紫燕. 基于尺度收缩法的山西乡镇级房屋结构数据研究分析. 山西科技, 2019, 34(6):122-127.]
[11]	Wang Ying, Shi Peijun, Wang Jing'ai. The housing loss assessment of rural villages caused by earthquake disaster in Yunnan Province. Acta Seismologica Sinica, 2005, 27(5):551-560, 582.
	[ 王瑛, 史培军, 王静爱. 云南省农村乡镇地震灾害房屋损失评估. 地震学报, 2005, 27(5):551-560, 582.]
[12]	Wang Lili, Li Lintong, Ren Xue, et al. Research of buildings' increasing regularity based on the data of the buildings' general survey. Journal of Disaster Prevention and Reduction, 2013, 29(3):9-12.
	[ 王丽莉, 李林侗, 任雪, 等. 基于房屋普查数据的房屋增长规律研究. 防灾减灾学报, 2013, 29(3):9-12.]
[13]	Liu Xingyuan. Discussion on security evaluation of multi-layered hybrid structured houses in Chongqing. Chongqing Architecture, 2016, 15(10):48-51.
	[ 刘兴远. 重庆市乡镇多层混合结构房屋安全性鉴定探讨. 重庆建筑, 2016, 15(10):48-51.]
[14]	Lin Chao. The discussion of the type of the rural settlements. Geography, 1938, 6(1):17-18.
	[ 林超. 聚落分类之讨论. 地理, 1938, 6(1):17-18.]
[15]	Chen Shupeng, Yang Lipu. Geography of settlement near Zunyi. Acta Geographica Sinica, 1943, 10:69-81.
	[ 陈述彭, 杨利普. 遵义附近之聚落. 地理学报, 1943, 10:69-81.] doi: 10.11821/xb194300004
[16]	Zhu Binhai. Distribution of mountainous villages in Xikang. Acta Geographica Sinica, 1939, 6(1):40-43.
	[ 朱炳海. 西康山地村落之分布. 地理学报, 1939, 6(1):40-43.] doi: 10.11821/xb193901005
[17]	Liu Enlan. Alpine settlements in western Sichuan. Acta Geographica Sinica, 1948, 15(Suppl.1):27-29.
	[ 刘恩兰. 川西之高山聚落. 地理学报, 1948, 15(S1):27-29.]
[18]	Yan Qinshang. Xikang residential geography. Acta Geographica Sinica, 1939, 6(1):43-58.
	[ 严钦尚. 西康居住地理. 地理学报, 1939, 6(1):43-58.] doi: 10.11821/xb193901006
[19]	Jin Qiming. The Rural Settlement Geography in China. Nanjing: Jiangsu Science and Technology Press, 1989.
	[ 金其铭. 中国农村聚落地理. 南京: 江苏科学技术出版社, 1989.]
[20]	Christaller Walter. Die Zentralen Orte in Süddeutschland. Chang Zhengyi, et al. trans. Beijing: The Commercial Press, 1998.
	[ 沃尔特·克里斯塔勒. 德国南部的中心地原理. 常正义, 等, 译. 北京: 商务印书馆, 1998.]
[21]	William Skinner G. Marketing and Social Structure in Rural China. Shi Jianyun, Xu Xiuli, trans. Beijing: China Social Sciences Press, 1998.
	[ 施坚雅. 中国农村的市场和社会结构. 史建云, 徐秀丽, 译. 北京: 中国社会科学出版社, 1998.]
[22]	Liu Peilin. On construction and utilization of Chinese traditional settlements landscape's genetic map[D]. Beijing: Peking University, 2011.
	[ 刘沛林. 中国传统聚落景观基因图谱的构建与应用研究[D]. 北京: 北京大学, 2011.]
[23]	Zheng Wanlin, Wang Zhigang. Design of a settlement residential space based on fractal structures and isomorphism: A case study on traditional Yi settlements in Chuxiong. South Architecture, 2021(5):130-137.
	[ 郑婉琳, 王志刚. 基于聚落分形同构研究的村镇人居空间设计: 以楚雄地区彝族传统聚落为例. 南方建筑, 2021(5):130-137.]
[24]	Su Jianmin, Yang Lanxin, Jing Weipeng. U-Net based semantic segmentation method for high resolution remote sensing image. Computer Engineering and Applications, 2019, 55(7):207-213.
	[ 苏健民, 杨岚心, 景维鹏. 基于U-Net的高分辨率遥感图像语义分割方法. 计算机工程与应用, 2019, 55(7):207-213.]
[25]	Chen D Y, Peng L, Li W C, et al. Building extraction and number statistics in WUI areas based on UNet structure and ensemble learning. Remote Sensing, 2021, 13(6):1172. DOI: 10.3390/rs13061172. doi: 10.3390/rs13061172
[26]	Boonpook W, Tan Y M, Ye Y H, et al. A deep learning approach on building detection from unmanned aerial vehicle: Based images in riverbank monitoring. Sensors (Basel, Switzerland), 2018, 18(11):3921-3933. doi: 10.3390/s18113921
[27]	Chen M, Wu J J, Liu L Z, et al. DR-net: An improved network for building extraction from high resolution remote sensing image. Remote Sensing, 2021, 13(2):294-311. doi: 10.3390/rs13020294
[28]	He K, Gkioxari G, Dollár P, et al. Mask R-CNN//Proceedings of the IEEE international conference on computer vision. 2017: 2961-2969.
[29]	Zhao K, Kang J, Jung J, et al. Building extraction from satellite images using Mask R-CNN with building boundary regularization//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2018: 247-251.
[30]	Zhang L L, Wu J S, Fan Y, et al. An efficient building extraction method from high spatial resolution remote sensing images based on improved mask R-CNN. Sensors (Basel, Switzerland), 2020, 20(5):1465-1477. doi: 10.3390/s20051465
[31]	Zhao Ruochen, Wang Jingdong, Lin Siyu, et al. Small building detection algorithm based on convolutional neural network. Systems Engineering and Electronics, 2021, 43(11):3098-3106.
	[ 赵若辰, 王敬东, 林思玉, 等. 基于卷积神经网络的小型建筑物检测算法. 系统工程与电子技术, 2021, 43(11):3098-3106.]
[32]	Stiller D, Stark T, Wurm M, et al. Large-scale building extraction in very high-resolution aerial imagery using Mask R-CNN. 2019 Joint Urban Remote Sensing Event (JURSE), 2019: 1-4.
[33]	Tiede D, Schwendemann G, Alobaidi A, et al. Mask R-CNN-based building extraction from VHR satellite data in operational humanitarian action: An example related to Covid-19 response in Khartoum, Sudan. Transactions in GIS, 2021, 25(3):1213-1227. doi: 10.1111/tgis.12766
[34]	Ji C, Tang H. Number of building stories estimation from monocular satellite image using a modified mask R-CNN. Remote Sensing, 2020, 12(22):3833-3849. doi: 10.3390/rs12223833
[35]	ISPRS 2D Semantic Labeling Contest, 2018. SPRS 2D Semantic Labeling Contest, 2018.http://www2.isprs.org/commissions/comm3/wg4/semantic-labeling.html.
[36]	Mnih V. Machine learning for aerial image labeling[D]. Toronto: University of Toronto, 2013.
[37]	Maggiori E, Tarabalka Y, Charpiat G, et al. Can semantic labeling methods generalize to any city? The Inria aerial image labeling benchmark//2017 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2017: 3226-3229.
[38]	Ji S P, Wei S Q, Lu M. Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(1):574-586. doi: 10.1109/TGRS.2018.2858817
[39]	Deng Dacai. Four paradigms beyond the village: A methodological perspective: A case study of Skinner, Friedman, Huang Zongzhi and Du Zanqi. Social Science Research, 2010(2):130-136.
	[ 邓大才. 超越村庄的四种范式: 方法论视角: 以施坚雅、弗里德曼、黄宗智、杜赞奇为例. 社会科学研究, 2010(2):130-136.]
[40]	Yu Huiming, Zhou Zhixiang, Peng Yang. A remote sensing image target recognition method based on improved Mask R-CNN model. Information Technology and Network Security, 2021, 40(3):38-42, 47.
	[ 余慧明, 周志祥, 彭杨, 等. 一种基于改进Mask R-CNN模型的遥感图像目标识别方法. 信息技术与网络安全, 2021, 40(3):38-42, 47.]
[41]	Gong P, Liu H, Zhang M N, et al. Stable classification with limited sample: Transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. Science Bulletin, 2019, 64(6):370-373. doi: 10.1016/j.scib.2019.03.002
[42]	Wu Liangyong. History of Human Settlement in China. Beijing: China Architecture & Building Press, 2014.
	[ 吴良镛. 中国人居史. 中国建筑工业出版社, 2014.]
[43]	Lin Zhiming, Zhang Ruixia, Tang Pinsen, et al. Panoramic town and village planning compilation and practice. Planners, 2014, 30(9):94-99.
	[ 林志明, 张瑞霞, 汤品森, 等. 全域视角下的镇域村镇布局规划编制探讨. 规划师, 2014, 30(9):94-99.]
[44]	Liu Yansui, Zhang Ziwen, Wang Jieyong. Regional differentiation and comprehensive regionalization scheme of modern agriculture in China. Acta Geographica Sinica, 2018, 73(2):203-218. doi: 10.11821/dlxb201802001
	[ 刘彦随, 张紫雯, 王介勇. 中国农业地域分异与现代农业区划方案. 地理学报, 2018, 73(2):203-218.] doi: 10.11821/dlxb201802001

密度梯队	农业区划 (仅包括有效识别的1409个农业县)	农业区基本信息				农房分布特征
密度梯队	农业区划 (仅包括有效识别的1409个农业县)	国土面积占比(%)	户籍人口占比(%)	耕地面积占比(%)	人均耕地 (m²/人)	建筑面积占比(%)	农房栋数占比(%)	镇域农房面积密度平均值 (m²/km²)	农房基尼系数
一	黄淮海区	4.50	24.50	18.80	1311	23.10	31.90	31311	0.31
二	长江中下游区	9.70	23.80	14.10	1012	28.30	19.20	20660	0.51
二	华南区	5.50	8.70	3.90	767	9.30	8.50	15363	0.58
三	西南区	13.30	21.80	8.00	628	20.90	16.30	12162	0.53
三	黄土高原区	7.10	9.50	10.10	1811	8.40	9.60	11944	0.60
四	甘新区	32.00	2.80	10.50	6510	3.80	4.90	6972	0.72
	内蒙古及长城沿线区	5.90	3.70	15.10	7033	2.50	4.00	4660	0.62
	东北区	7.00	4.40	18.40	7087	2.90	5.20	4550	0.55
五	青藏区	15.10	0.90	1.10	2135	0.70	0.50	713	0.72

基于遥感解译的中国农房空间分布特征分析

Spatial distribution of rural building in China: Remote sensing interpretation and density analysis

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 44

相关文章 15

Metrics

本文评价

[1]	刘云刚, 王韬. 中国政治地理学研究进展评述[J]. 地理学报, 2022, 77(6): 1506-1517.
[2]	孙三百, 张青萍, 李冉, 张可云. 中国地区收入与净财富不平等的演变路径识别[J]. 地理学报, 2022, 77(6): 1411-1429.
[3]	吴思栩, 孙斌栋, 张婷麟. 互联网对中国城市内部就业分布的动态影响[J]. 地理学报, 2022, 77(6): 1446-1460.
[4]	饶志国, 秦倩倩, 魏士凯, 郭海春, 李云霞. 全新世温度研究回顾及对历史人地关系的启示[J]. 地理学报, 2022, 77(5): 1169-1180.
[5]	陈泓瑾, 刘琳, 张正勇, 刘亚, 田浩, 康紫薇, 王统霞, 张雪莹. 天山北坡人类活动强度与地表温度的时空关联性[J]. 地理学报, 2022, 77(5): 1244-1259.
[6]	匡文慧, 张树文, 杜国明, 颜长珍, 吴世新, 李仁东, 陆灯盛, 潘涛, 宁静, 郭长庆, 董金玮, 包玉海, 迟文峰, 窦银银, 侯亚丽, 尹哲睿, 常丽萍, 杨久春, 谢家丽, 邱娟, 张汉松, 张宇博, 杨仕琪, 萨日盖, 刘纪远. 2015—2020年中国土地利用变化遥感制图及时空特征分析[J]. 地理学报, 2022, 77(5): 1056-1071.
[7]	王秀伟, 李晓军. 中国乡村旅游重点村的空间特征与影响因素[J]. 地理学报, 2022, 77(4): 900-917.
[8]	刘长生, 陈昀, 简玉峰, 董瑞甜. 中国旅游产业发展间接就业带动能力测算及其时空差异[J]. 地理学报, 2022, 77(4): 918-935.
[9]	曹湛, 戴靓, 杨宇, 彭震伟. 基于“蜂鸣—管道”模型的中国城市知识合作模式及其对知识产出的影响[J]. 地理学报, 2022, 77(4): 960-975.
[10]	张启楠, 张凡凡, 麦强, 伍国勇. 中国粮食生产效率空间溢出网络及提升路径[J]. 地理学报, 2022, 77(4): 996-1008.
[11]	胡晓阳, 王兆锋, 张镱锂, 宫殿清. 青藏高原放牧强度空间化方法与应用[J]. 地理学报, 2022, 77(3): 547-558.
[12]	宋飏, 刘艳晓, 张瑜, 王士君. 中国手足口病时空分异特征及影响因素[J]. 地理学报, 2022, 77(3): 574-588.
[13]	梁鑫源, 金晓斌, 孙瑞, 韩博, 任婕, 周寅康. 多情景粮食安全底线约束下的中国耕地保护弹性空间[J]. 地理学报, 2022, 77(3): 697-713.
[14]	杨宇. 中国与全球能源网络的互动逻辑与格局转变[J]. 地理学报, 2022, 77(2): 295-314.
[15]	朱晟君, 杨博飞, 刘逸. 经济全球化变革下的世界经济地理与中国角色[J]. 地理学报, 2022, 77(2): 315-330.