面向对象的高分辨率遥感影像建筑物信息提取

大气与环境光学学报 ›› 2021, Vol. 16 ›› Issue (4): 358-364.

面向对象的高分辨率遥感影像建筑物信息提取

韩东成1;2∗, 杨世植1, 赵强3, 韩露1;2, 杨志3, 崔生成1

1 中国科学院合肥物质科学研究院安徽光学精密机械研究所, 中国科学院大气光学重点实验室, 安徽合肥 230031; 2 中国科学技术大学, 安徽合肥 230022; 3 安徽建筑大学环境与能源工程学院, 安徽合肥 23061

收稿日期:2019-05-23 修回日期:2020-02-01 出版日期:2021-07-28 发布日期:2021-07-28
通讯作者: hdc@dcustc.com E-mail:1039433532@qq.com
作者简介:韩东成 (1992 - ), 安徽阜阳人, 硕士研究生, 主要从事遥感图像处理与目标识别方面的研究。 E-mail: hdc@dcustc.com
基金资助:
Supported by Anhui Provincial Natural Science Foundation (安徽省自然科学基金项目, 1508085SQD208), First Phase Project of Urban Fine Management Remote Sensing Application Demonstration System (高分城市精细化管理遥感应用示范系统 (一期) 项目, 06-Y30B04-9002-13/15), The Science and Technology Plan project of Housing and Urban-Rural Development of Anhui Province (安徽省住房城乡建设科学技术计划项目, 2020-SF10), Key Project of Anhui Provincial University Excellent Young Talents Support Program (安徽省高校优秀青年人才支持计划重点项目, gxyqZD2020036)

Object-Oriented Building Information Extraction from High Resolution Remote Sensing Satellite Imagery

HAN Dongcheng1;2∗, YANG Shizhi1, ZHAO Qiang3, Han Lu1;2, YANG zhi3, CUI Shengcheng1

1 Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, HFIPS, Chinese Academy of Sciences, Hefei 230031, China; 2 University of Science and Technology of China, Hefei 230022, China; 3 School of Environment and Energy Engineering, Anhui Jianzhu University, Hefei 230601, China

Received:2019-05-23 Revised:2020-02-01 Published:2021-07-28 Online:2021-07-28
Contact: Dong-Cheng HAN E-mail:1039433532@qq.com
Supported by:
Anhui Provincial Natural Science Foundation

摘要/Abstract

摘要： 为实现建筑物单体信息的高精度提取, 采用基于规则的面向对象方法, 提出了一种经图像预处理、多尺度分割、构建规则信息和特征提取的技术流程。以基于国产高分二号卫星的扬州市两个样本区 (佳家花园小区和联谊南苑小区) 为例对该方法进行了实验验证, 研究结果表明: 与传统方法相比, 新方法提取的效果更好、精度更高, 识别精度达到 97.7%, Kappa 系数为 0.93。

关键词: 规则数据库, 面向对象, 信息提取, 高分辨率遥感影像, 建筑物

Abstract: In order to achieve high-precision building information extraction, a rule-based object-oriented method is adopted, and a technical process of image preprocessing, multi-scale segmentation, construction of rule information, and feature extraction is proposed. Two sample areas in Yangzhou City, China (Jiajia Garden Community and Lianyi Nanyuan Community) based on the domestically produced GF-2 satellite are used for experimental validation of the method. It is shown that compared with the traditional method, the new method has better extraction effect and higher accuracy, with a recognition accuracy of 97.7% and a Kappa coefficient of 0.93.

Key words: rule database, object-oriented, information extraction, high resolution remote sensing image, building

中图分类号:

P237

韩东成, ∗, 杨世植, 赵强, 韩露, 杨志, 崔生成. 面向对象的高分辨率遥感影像建筑物信息提取[J]. 大气与环境光学学报, 2021, 16(4): 358-364.

HAN Dongcheng, ∗, YANG Shizhi, ZHAO Qiang, Han Lu, YANG zhi, CUI Shengcheng. Object-Oriented Building Information Extraction from High Resolution Remote Sensing Satellite Imagery[J]. Journal of Atmospheric and Environmental Optics, 2021, 16(4): 358-364.

参考文献 12

[1]	Zhao Qiang, Yang Zhi, Su Hongchao, et al. Building height extraction based on GF-2 satellite remote sensing data [J]. Journal
	of Atmospheric and Environmental Optics, 2019, 14(6): 455-462.
	赵强, 杨志, 苏红超, 等. 基于高分二号卫星遥感数据的建筑物高度提取 [J]. 大气与环境光学学报, 2019, 14(6): 455-462.
[2]	Liu Yonghong, Niu Zheng, Wang Changyao. Research and application of the decision tree classification using MODIS data
[J]	Journal of Remote Sensing, 2005, 9(4): 405-412.
	刘勇洪, 牛铮, 王长耀. 基于 MODIS 数据的决策树分类方法研究与应用 [J]. 遥感学报, 2005, 9(4): 405-412.
[3]	Cao Xue, Ke Changqing. Classification of high-resolution remote sensing images using object-oriented method [J]. Remote
	Sensing Information, 2006, 21(5): 27-30,51,73.
	曹雪, 柯长青. 基于对象级的高分辨率遥感影像分类研究 [J]. 遥感信息, 2006, 21(5): 27-30,51,73.
[4]	Sun Xiaoxia, Zhang Jixian, Liu Zhengjun. Extracting the river and the road using an object oriented technique from IKONOS
	panchromatic imagery [J]. Science of Surveying and Mapping, 2006, 31(1): 62-63.
	孙晓霞, 张继贤, 刘正军. 利用面向对象的分类方法从 IKONOS 全色影像中提取河流和道路 [J]. 测绘科学, 2006, 31(1):
62	-63.
[5]	Xu Hanqiu. Fast information extraction of urban built-up land based on the analysis of spectral signature and normalized
	difference index [J]. Geographical Research, 2005, 24(2): 311-320.
	徐涵秋. 基于谱间特征和归一化指数分析的城市建筑用地信息提取 [J]. 地理研究, 2005, 24(2): 311-320.
[6]	Fan Shudi, Hu Yueming, Liu Zhenhua. Research of information extraction of city building based on a new object-oriented
	method [J]. Journal of South China Normal University (Natural Science Edition), 2015, 47(6): 91-97.
	樊舒迪, 胡月明, 刘振华. 一种新的面向对象城市建筑物信息提取方法研究 [J]. 华南师范大学学报 (自然科学版), 2015,
47	(6): 91-97.
[7]	Guo Yifan, Zhang Jin, Wei Dong. Wei Dong. Research on object oriented high-resolution remote sensing Image of building
	contour extraction [J]. Bulletin of Surveying and Mapping, 2014, (Sup 2):300-303.
	郭怡帆, 张锦, 卫东. 面向对象的高分辨率遥感影像建筑物轮廓提取研究 [J]. 测绘通报, 2014 (增刊 2): 300-303.
[8]	Han Dongcheng. Research on Building Information Extraction Based on GF-2 Remote Sensing Satellite [D]. Hefei: University
	of Science and Technology of China, 2019.
	韩东成. 基于高分二号遥感卫星的建筑物信息提取研究 [D]. 合肥: 中国科学技术大学, 2019.
[9]	Yu Hui, Chen Xiaoting, Wang Jinhua. Object-oriented image information extraction based on first satellite with high resolution
[J]	Journal of North China University of Science and Technology (Natural Science Edition), 2017, 39(1): 6-11.
	于辉, 陈晓停, 汪金花. 基于高分一号的面向对象影像信息提取 [J]. 华北理工大学学报 (自然科学版), 2017, 39(1): 6-11.
[10]	Koepfler G, Lopez C, Morel J M. A multiscale algorithm for image segmentation by variational method [J]. SIAM Journal on
	Numerical Analysis, 1994, 31(1): 282-299.
[11]	Hu Jingang, Zhang Xiaodong, Shen Xin, et al. A method of road extraction in high-resolution remote sensing imagery based
	on object-oriented image analysis [J]. Remote Sensing Technology and Application, 2006, 21(3): 184-188.
	胡进刚, 张晓东, 沈欣, 等. 一种面向对象的高分辨率影像道路提取方法 [J]. 遥感技术与应用, 2006, 21(3): 184-188.
[12]	McFeeters S K. The use of the normalized difference water index (NDWI) in the delineation of open water features [J].
	International Journal of Remote Sensing, 1996, 17(7): 1425-1432.