Please wait a minute...
浙江大学学报(工学版)  2019, Vol. 53 Issue (1): 137-145    DOI: 10.3785/j.issn.1008-973X.2019.01.015
计算机技术     
基于背景类别分层分离的不透水面间接提取——以兰州城关区EO-1 ALI图像为例
刘炜, 王聪华, 赵尔平, 雒伟群
西藏民族大学 信息工程学院, 西藏光信息处理与可视化技术重点实验室, 陕西 咸阳 712082
Impervious surface extraction based on stratified removal of contexts types-take EO-1 ALI image of Chengguan county in Lanzhou as example
LIU Wei, WANG Cong-hua, ZHAO Er-ping, LUO Wei-qun
Xizang Key Laboratory of Optical Information Processing and Visualization Technology, College of Information Engineering, Xizang Minzu University, Xianyang 712082, China
 全文: PDF(2025 KB)   HTML
摘要:

以兰州市城关区EO-1 ALI图像作为基础数据源,对比LOOC与最邻近分类(NNC)方法提取不透水面的精度差异. LOOC方法对融合后EO-1 ALI图像进行LBV变换,将变换结果作为解译底图;设置4个尺度层次,分别对应水体、农用地、灌木林地、城市绿地和草地这5种主要背景类别,对解译底图执行4尺度面向对象分割;将上述类别对象的光谱特征和形态特征差异作为判别规则,利用决策树分类,将这5种背景类别依次从解译底图上提取、分离,生成不透水面初级提取图层;通过光谱反射率差异分析,选定EO-1 ALI图像的近红外波段8和中红外波段10作为分类特征,利用基于模糊C-均值(FCM)算法的非监督分类,从初级图层中分离出砂土、阴影这两种与高、低反照度不透水面光谱特征相近的类别,采用数学形态学开闭运算整饬图像,生成不透水面二级提取图层. 结合目视评判和总体精度、Kappa系数,定量分析LOOC方法与NNC方法的提取精度差异. 结果表明:LOOC方法提取不透水面的总体精度、Kappa系数分别为87.13%、0.830 3,较NNC方法分别提高5.91%、7.19%. LOOC方法依据各背景类别的遥感多特征知识,分两级将其分离出解译底图,从而间接、逐步逼近不透水面精准空间分布信息,辨识不透水面的效率优于NNC方法.

Abstract:

The most suitable method for impervious surface extraction was adopted by using EO-1 ALI image of Chengguan County in Lanzhou. The supervised classification based on LOOC and nearest neighbor classification (NNC) was compared. LBV transform was conducted for EO-1 ALI image. Then the image was offered as interpretation base map for further processing. Four scale levels were set in interpretation base map to match 5 kinds of contexts types, including waters/farmland/shrub land/urban green space and meadow. Then object-oriented segmentation was conducted in interpretation base map to get polygon objects of each context types. The decision tree classification was conducted to dislodge out cover information of above-mentioned contexts types in interpretation base map based on spectral features and shape feature of polygon objects of each context type. Then primary layer of impervious surface was obtained from interpretation base map. The unsupervised classification based on fuzzy C-mean (FCM) algorithm was carried to dislodge out another 2 kinds of contexts types from primary layer of impervious surface, including shadow of landform and sandy soil. Band 8 and band 10 of EO-1 ALI image was selected as effective feature in the process of unsupervised classification. Then secondary layer of impervious surface was obtained. The subject and object standard were adopted to evaluate the classification precision for three methods, including LOOC/NNC. Results showed that classification accuracy and Kappa coefficient was 87.13%, 0.830 3 by using the method of LOOC. Growth of 5.91% for overall classification accuracy and 7.19% for Kappa coefficient were achieved compared with NNC. The method of LOOC can provide more accurate extraction results for impervious surface using EO-1 ALI image compared with NCC.

收稿日期: 2017-07-16 出版日期: 2019-01-07
CLC:  TP753  
基金资助:

国家自然科学基金资助项目(41361044,61162025)

通讯作者: 王聪华,男,教授,博士.orcid.org/0000-0003-4815-3324.     E-mail: wangcshui@126.com
作者简介: 刘炜(1976-),男,副教授,博士,从事土地遥感与GIS应用技术研究.orcid.org/0000-0002-4813-3668.E-mail:remote2009@126.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  

引用本文:

刘炜, 王聪华, 赵尔平, 雒伟群. 基于背景类别分层分离的不透水面间接提取——以兰州城关区EO-1 ALI图像为例[J]. 浙江大学学报(工学版), 2019, 53(1): 137-145.

LIU Wei, WANG Cong-hua, ZHAO Er-ping, LUO Wei-qun. Impervious surface extraction based on stratified removal of contexts types-take EO-1 ALI image of Chengguan county in Lanzhou as example. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2019, 53(1): 137-145.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.01.015        http://www.zjujournals.com/eng/CN/Y2019/V53/I1/137

[1] 宋瑞祥, 张庆国, 于海敬, 等. 遥感数据的城市不透水面估算及增温效应[J]. 浙江大学学报:工学版, 2017, 51(5):1501-1506 SONG Rui-xiang, ZHANG Qing-guo, YU Hai-jing, et al. Estimations to impervious surface and their effects of warming for ctiy using remote data[J]. Journal of Zhejiang University:Engineering Science, 2017, 51(5):1501-1506
[2] 姚磊, 卫伟, 于洋, 等. 基于GIS和RS技术的北京市功能区产流风险分析[J]. 地理学报, 2015, 70(2):308-318 YAO Lei, WEI Wei, YU Yang, et al. Research on potential runoff risk of urban functional zonesin Beijing city based on GIS and RS[J]. Acta Geographica Sinica, 2015, 70(2):308-318
[3] 张甜, 王仰麟, 刘焱序, 等. 1987-2015年深圳市主城区景观演变过程多时相识别[J]. 地理学报, 2016, 76(12):2170-2184 ZHANG Tian, WANG Yang-lin, LIU Yan-xu, et al. Multi-temporal detection of landscape evolutionin western Shenzhen City during 1987-2015[J]. Acta Geographica Sinica, 2016, 76(12):2170-2184
[4] 李苗, 臧淑英, 吴长山, 等. 哈尔滨市城乡结合部不透水面时空变化及驱动力分析[J]. 地理学报, 2017, 72(1):105-115 LI Miao, ZANG Shu-ying, WU Chang-shan, et al. Spatial and temporal variation and its driving forces of urbanimpervious surface in urban-rural continuum of Harbin[J]. Acta Geographica Sinica, 2017, 72(1):105-115
[5] 张涛, 刘军, 杨可明, 等. 结合Gram-Schmidt变换的高光谱影像谐波分析融合算法[J]. 测绘学报, 2015, 44(9):1042-1047 ZHANG Tao, LIU Jun, YANG Ke-ming, et al. Fusion algorithm for hyperspectral remote sensing image combined with harmonic analysis and Gram-Schmidt transform[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(9):1042-1047
[6] 唐菲, 徐涵秋. 不同传感器线性光谱分解反演不透水面的对比-以Landsat ETM+和EO-1ALI为例[J]. 武汉大学学报:信息科学版, 2013, 38(9):1065-1072 TANG Fei, XU Han-qiu. A LSMA-based comparison of the performances in retriecving imperviosu surface between Landsat ETM+ and EO-1 ALI[J]. Geomatics and Information Science of Wuhan University, 2013, 38(9):1065-1072
[7] 李博, 晏磊, 张立福. 传感器光谱指标对植被光谱模拟精度的影响[J]. 光谱学与光谱分析, 2010, 30(7):1843-1847 LI Bo, YAN Lei, ZHANG Li-fu. Evaluation of sensor spectral parameters for the simulation accuracy of the vegetation spectrum[J]. Spectroscopy and Spectral Analysis, 2010, 30(7):1843-1847
[8] 臧淑英, 冯仲科. 资源型城市土地利用/土地覆被变化与景观动态:大庆市案例分析[M]. 北京:科学出版社, 2008.
[9] 徐涵秋, 王美雅. 地表不透水面信息遥感的主要方法分析[J]. 遥感学报, 2016, 20(5):1270-1289 XU Han-qiu, WANG Mei-ya. Remote sensing-based retrieval of ground impervious surfaces[J]. Journal of Remote Sensing, 2016, 20(5):1270-1289
[10] 李玮娜, 杨建生, 李晓, 等. 基于TM图像的城市不透水面信息提取[J]. 国土资源遥感, 2013, 25(1):66-70 LI Wei-na, YANG Jian-sheng, LI Xiao, et al. Extraction of imperious surface imformation from TM image[J]. Remote Sensing for Land and Resources, 2013, 25(1):66-70
[11] 王浩, 吴炳方, 李晓松, 等. 流域尺度的不透水面遥感提取[J]. 遥感学报, 2011, 15(2):388-400 WANG Hao, WU Bing-fang, LI Xiao-song, et al. Extraction of impervious surface in Hai Basin using remote sensing[J]. Journal of Remote Sensing, 2011, 15(2):388-400
[12] 陈峰, 邱全意, 郭青海, 等. CBERS-02B多光谱数据在城市不透水面估算中的可用性研究[J]. 遥感学报, 2011, 15(3):621-639 CHEN Feng, QIU Quan-yi, GUO Qing-hai, et al. The availability of CBERS-02B multi-spectral data in estimating urban impervious surface[J]. Journal of Remote Sensing, 2011, 15(3):621-639
[13] 唐菲, 徐涵秋. 高光谱与多光谱遥感影像反演地表不透水面的对比-以Hyperion和TM/ETM+为例[J]. 光谱学与光谱分析, 2014, 34(4):1075-1080 TANG Fei, XU Han-qiu. Comparison of performances in retrieving impervious surface between hyper-spectral (Hyperion) and multispectral (TM/ETM+) images[J]. Spectroscopy and Spectral Analysis, 2014, 34(4):1075-1080
[14] 曹丽琴, 李平湘, 张良培, 等. Fuzzy ARTMAP算法在城市不透水面估算中的应用研究[J]. 武汉大学学报:信息科学版, 2012, 37(10):1236-1239 CAO Li-qin, LI Ping-xiang, ZHANG Liang-pei, et al. Estimating Impervious surfaces using the fuzzy ARTMAP[J]. Geomatics and Information Science of Wuhan University, 2012, 37(10):1236-1239
[15] 张路, 高志宏, 廖明生, 等. 利用多源遥感数据进行城市不透水面覆盖度估算[J]. 武汉大学学报:信息科学版, 2010, 35(10):1212-1216 ZHANG Lu, GAO Zhi-hong, LIAO Ming-sheng, et al. Estimating urban impervious surface percentage with multi-source remote sensing data[J]. Geomatics and Information Science of Wuhan University, 2010, 35(10):1212-1216
[16] 曾志远. 卫星遥感图像计算机分类与地学应用研究[M]. 北京:科学出版社, 2004.
[17] 马利刚, 张乐平, 邓劲松, 等. 资源一号"02C"遥感影像土地利用分类[J]. 浙江大学学报:工学版, 2013, 47(8):1508-1516 MA Li-gang, ZHANG Le-ping, DENG Jin-song, et al. Land use classification using ZY1-"02C"remote sensing images[J]. Journal of Zhejiang University:Engineering Science, 2013, 47(8):1508-1516
[18] 胡荣明, 黄小兵, 黄远程. 增强形态学建筑物指数应用于高分辨率遥感影像中建筑物提取[J]. 测绘学报, 2014, 43(5):514-520 HU Rong-ming, HUANG Xiao-bing, HUANG Yuan-cheng. An enhanced morphological building index for buidling extraction from high-resolution image[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(5):514-520
[19] 杜培军, 谭琨, 夏俊士, 等. 城市环境遥感方法与实践[M]. 北京:科学出版社, 2013:208-223.
[20] 周亚男, 骆剑承, 程熙, 等. 多特征融入的自适应遥感影像多尺度分割[J]. 武汉大学学报:信息科学版, 2013, 38(1):19-22 ZHOU Ya-nan, LUO Jian-cheng, CHENG Xi, et al. Land use and land cover classification and verification in Northern Shaanxi Loess Plateau[J]. Geomatics and Information Science of Wuhan University, 2013, 38(1):19-22

No related articles found!