基于Landsat-8与ZY3多源遥感影像的城镇居民地识别与再分类研究

地震 ›› 2015, Vol. 35 ›› Issue (3): 123-135.

基于Landsat-8与ZY3多源遥感影像的城镇居民地识别与再分类研究

李振敏, 王晓青, 窦爱霞, 杨海霞, 黄树松, 崔丽萍

中国地震局地震预测研究所, 北京 100036

收稿日期:2015-01-27 出版日期:2015-07-31 发布日期:2020-06-28
作者简介:李振敏(1988-), 女, 新疆乌鲁木齐人, 在读硕士研究生, 主要从事遥感与GIS应用等研究。
基金资助:
“十二五”科技支撑课题(2012BAK15B02)

Extraction and Re-classification of Urban Residential Area Based on Landsat-8 and ZY3 Multi-source Remote Sensing Images

LI Zhen-min, WANG Xiao-qing, DOU Ai-xia, YANG Hai-xia, HUANG Shu-song, CUI Li-ping

Institute of Earthquake Science, CEA, Beijing 100036, China

Received:2015-01-27 Online:2015-07-31 Published:2020-06-28

摘要/Abstract

摘要： 精细的居民地数据对地震灾害风险分析具有重要意义。为得到具有较高时效性与精细度的居民地数据, 充分发挥其对人口、建筑物空间展布的指示作用, 本文综合利用多源遥感影像的优势, 基于分层分类思想开展城镇居民地识别与再分类研究。以甘肃天水秦州区的主城区为例, 采用具有较高时效性的Landsat-8 OLI影像, 建立决策树分类模型识别出居民地轮廓; 在居民地轮廓内部, 进一步采用资源三号卫星(ZY3)高分影像, 利用面向对象方法进行居民地内部的建筑群再分类, 最后得到了具有不同精细程度的居民地数据。实验结果中Landsat-8土地覆盖分类总体精度为92%(其中居民地识别率达86%), 城镇居民地再分类的总体精度为81%, 说明了本文研究方案的可行性。

关键词: 居民地遥感识别, 分层分类, Landsat-8, 地震风险分析

Abstract: Detailed residential area (ResA) distribution data have significances to seismic risk analysis. In order to obtain more detailed ResA data with higher timeliness, and give their full play in indicating the spatial distribution of population and buildings, we integrated the advantages of multi-source RS images, and carried out the extraction and re-classification research of urban ResA based on hierarchical classification method. With Qinzhou District, Tianshui, Gansu Province of China as study area, we used new Landsat-8 OLI image to classify urban land-use and recognize the holistic ResA through building a decision tree classification model. Inside the urban ResA, we further used domestic ZY3 satellite image to re-classify the land-use and buildings based on object-oriented method. Finally the ResA data with different levels of detail were obtained. The overall land-use classification precision of Landsat-8 image was about 92% (the recognition rate of ResA was 86%), and the re-classification precision of buildings inside urban ResA is 81% (only consumed half of the time). It indicated that based on multi-source RS images, the hierarchical classification method is available to extract and re-classify urban ResA.

Key words: Residential area extraction, Earthquake risk analysis, Hierarchical classification, Landsat-8

中图分类号:

P315.7

李振敏, 王晓青, 窦爱霞, 杨海霞, 黄树松, 崔丽萍. 基于Landsat-8与ZY3多源遥感影像的城镇居民地识别与再分类研究[J]. 地震, 2015, 35(3): 123-135.

LI Zhen-min, WANG Xiao-qing, DOU Ai-xia, YANG Hai-xia, HUANG Shu-song, CUI Li-ping. Extraction and Re-classification of Urban Residential Area Based on Landsat-8 and ZY3 Multi-source Remote Sensing Images[J]. EARTHQUAKE, 2015, 35(3): 123-135.

参考文献

[1] 金夏玲. 基于分层分类的居民地信息提取方法研究[D]. 河海大学, 2005.
[2] 宁宝坤, 曲国胜, 张宁. 遥感技术在地震灾害风险评估中的应用研究[C]. 中国北京: 2004.
[3] 蔡宗文, 危福泉, 方瑞峰, 等. 基于居民地分布的震害快速评估方法[J]. 中国地震, 2007, 23(04): 410-415.
[4] 陈振拓. 服务于地震应急的人口数据格网化方法研究[D]. 中国地震局地质研究所, 2012.
[5] 赵萍, 冯学智, 林广发. SPOT卫星影像居民地信息自动提取的决策树方法研究[J]. 遥感学报, 2003, (04): 309-315.
[6] Gong P, Howarth P J. The use of structural information for improving land-cover classification accuracies at the rural-urban fringe[J]. Photogrammetric Engineering and Remote Sensing, 1990, 56(1): 61-73.
[7] 康相武, 吴绍洪, 戴尔阜, 等. 区域社会经济财产数据空间化方法研究[J]. 中国软科学, 2006, (8): 104-108.
[8] 闫庆武, 卞正富. 基于GIS的社会统计数据空间化处理方法[J]. 云南地理环境研究, 2007, 19(2): 92-97.
[9] 曹治国, 陈华. IKONOS卫星图像的快速三维场景重建[J]. 计算机与数字工程, 2006, 34(11): 9-11.
[10] Hofmann P. Detecting informal settlements from IKONOS image data using methods of object oriented image analysis an example from cape town(South Africa)[C]. Regensburg: 2011.
[11] 张风霖, 缑变彩, 李靖琳. Landsat7 ETM+与Landsat8 OLI植被和非植被定量研究[J]. 山西建筑, 2014, (11): 240-241.
[12] 张风霖, 李婧琳, 缑变彩, 等. 基于Landsat8卫星OLI的水体信息提取研究[J]. 山西建筑, 2014, (23): 243-244.
[13] 刘礼, 于强. 分层分类与监督分类相结合的遥感分类法研究[J]. 林业调查规划, 2007, 32(04): 37-39.
[14] Friedl M A, Brodley C E. Decision tree classification of land cover from remotely sensed data[J]. Remote Sensing of Environment, 1997, 61(3): 399-409.
[15] J H G, J M D, P D. A Multi-scale Framework for Landscape Analysis: Object-specific analysis and up scaling[J]. Landscape Ecology, 2001, (16): 233-256.
[16] 杨慧, 郑思莉, 唐赫, 等. 面向对象的武汉市街区公共遥感影像分类研究[J]. 软件导刊, 2014, 13(01): 144-146.
[17] Cortes C, Vapnik V. Support-vector networs[J]. Machine Learning, 1995, 20(3): 273-297.
[18] 赵洁, 李玮, 郝志鹏, 等. 基于改进Canny算子与图像形态学融合的边缘检测方法[J]. 微型机与应用, 2011, 30(10): 44-47.
[19] http:∥landsat.usgs.gov/index.php[Z].
[20] 赵英时. 遥感应用分析原理与方法[M]. 科学出版社, 2011: 478.
[21] Software: Spectral Image Exploitation-FLAASH[M]. US Air Force Research Laboratory & Spectral Sciences Inc. http:∥www.spectral.com/FLAASH.shtml.
[22] Carrera-Hernández J J, Gaskin S J. The groundwater modeling tool for GRASS (GMTG): Open source groundwater flow modeling[J]. Computers & Geosciences, 2006, 32(3): 339-351.
[23] 吴志杰, 赵书河. 基于TM图像的“增强的指数型建筑用地指数”研究[J]. 国土资源遥感, 2012, (02): 50-55.
[24] 徐涵秋. 利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究[J]. 遥感学报, 2005, 9(05): 589-595.
[25] Congalton R G, Oderwald R G, Mead R A. Assessing Landsat classification accuracy using discrete multivariate statistical techniques[J]. Photogramm. Eng. Remote Sens, 1983, 12(49): 1671-1678.