Please wait a minute...
img

官方微信

遥感技术与应用  2016, Vol. 31 Issue (1): 194-202    DOI: 10.11873/j.issn.1004-0323.2016.1.0194
数据与图像处理     
联合快舟一号影像纹理信息的城市土地覆盖分类
潘一凡,张显峰,于泓峰,饶俊峰
(北京大学遥感与地理信息系统研究所,北京100871)
Land Cover Classification in Shihezi City by Combing the KZ-1 Texture and Landsat-8 OLI Spectral Information
 全文: PDF(6129 KB)  
摘要:

仅依靠光谱信息无法满足高分辨率遥感分类的应用需求,辅之以纹理特征信息进行分类,可提高影像分类精度。利用KZ\|1卫星影像和Landsat\|8卫星影像数据,基于面向对象的影像分割法和灰度共生矩阵纹理分析法对新疆石河子市局部城区进行了地表覆盖分类实验,将不同空间分辨率的全色影像纹理信息、光谱信息构成多种影像特征组合进行分类比较研究,以选择最佳的分类特征集。结果表明:KZ-1影像能为城市区域的土地覆盖分类提供丰富的纹理信息,面向对象的影像分割可较好地利用高分辨率数据的几何结构信息实现优化的影像分割,从而提高多光谱影像的分类精度,总体分类精度为90.06%,Kappa系数为87.93%,比单纯利用光谱信息分类的总体精度提高了8.02%,Kappa系数提高了9.65%,表明KZ\|1数据可为光谱分类提供丰富的纹理信息,从而提高城市区域的土地覆盖分类精度。

关键词: 分类;快舟一号(KZ-1)Landsat-8纹理影像分割城市区域    
Abstract:

Conventional remote sensing image classification is usually based on the spectral information and can’t perform well in the classification of high spatial resolution imagery.This study presents an approach to improve the classification accuracy by combining spectral information with spatial texture features to extract from high spatial resolution bands.The KZ\|1 image and Landsat\|8 image of a portion of Shihezi City,Xinjiang were acquired and preprocessed in the study.Object\|oriented image segmentation and grey\|level co\|occurrence matrix texture analysis were used to create image objects and extract textural features for object\|oriented classification.An optimal window size and threshold values were first determined for the image segmentation operation,and the support vector machine algorithm was used to perform the classification procedure.Eight textural features such as Mean,Variance,Homogeneity,Contrast,Dissimilarity,Entropy,Angular Second Moment,and Correlation were extracted from the KZ\|1 and Lansat\|8 OLI panchromatic bands and used to create several different feature sets to conduct the SVM classifications.Classification results from these various image feature sets indicate that due to its high spatial resolution the KZ\|1 image containing abundant textural information in the study area which can achieve the classification accuracy with overall accuracy of 90.06%,and Kappa coefficient of 87.93%.Compared with conventional spectral classification,the overall accuracy of the textural classification with KZ\|1 imagery is increased by 8.02%,and Kappa coefficient increased by 9.65%.The proposed approach is valuable for combing remotely sensed imagery from different satellite platforms to extract urban expansion information quickly and accurately in Xinjiang.

Key words: Classification    KZ-1;    andsat-8    Texture    Image segmentation    Urban areas
收稿日期: 2014-09-30 出版日期: 2016-04-05
:  TP 751  
基金资助:

国家973计划项目(2012BAH27B02、2012BAH27B03),新疆兵团援疆项目(2014AB021)。
              

通讯作者: 张显峰(1967-),男,北京人,博士,教授,主要从事环境遥感等方面的研究。Email:xfzhang@pku.edu.cn。    
作者简介: 潘一凡(1989-),男,山东济宁人,博士研究生,主要从事高光谱遥感和生态遥感等方面的研究。Email:yfpan@pku.edu.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  
潘一凡
张显峰
于泓峰
饶俊峰

引用本文:

潘一凡,张显峰,于泓峰,饶俊峰. 联合快舟一号影像纹理信息的城市土地覆盖分类[J]. 遥感技术与应用, 2016, 31(1): 194-202.

链接本文:

http://www.rsta.ac.cn/CN/Y2016/V31/I1/194

[1]Li Zhifeng,Zhu Guchang,Dong Taifeng.Application of GLCM-based Texture Features to Remote Sensing Image Classification[J].Geology and Exploration,2011,47(3):456-461.[李智峰,朱谷昌,董泰锋.基于灰度共生矩阵的图像纹理特征地物分类应用[J].地质与勘探,2011,47(03):456-461.]

[2]Mller-Jensen L.Methods for Texture-based Classification of Urban Fringe Areas from Medium and High Resolution Satellite Imagery[M].Dordrecht:In Spatial Inequalities,J.R.Weeks,A.G.Hill,J.Stoler,Editors,Springer Netherlands,2013:73-86.

[3]Zhang Q,Wang J,Gong P,et al.Study of Urban Spatial Patterns from SPOT Panchromatic Imagery Using Textural Analysis[J].International Journal of Remote Sensing,2003,24(21):4137-4160.

[4]Pesaresi M.Texture Analysis for Urban Pattern Recognition Using Fine-resolution Panchromatic Satellite Imagery[J].Geographical & Environmental Modelling,2000,4(1):43-63.

[5]Agüera F,Aguilar F J,Aguilar M A.Using Texture Analysis to Improve Per-pixel Classification of Very High Resolution Images for Mapping Plastic Greenhouses[J].ISPRS Journal of Photogrammetry and Remote Sensing,2008,63(6):635-646.

[6]Wu Lulu,Cao Menglei,Li Yi,et al.Research on Building Type Recognition based on Texture Analysis[C]//Wuhan Institute of Technology.Proceedings of 2010 International Conference on Remote Sensing (ICRS2010) Volume 4.Hangzhou China:Wuhan Institute of Technology,2010:4.[吴露露,曹孟磊,李毅,等.基于纹理分析的城市建筑物类型识别分析与研究[C]//武汉工程大学学报研究会.2010年国际遥感会议论文集(4).杭州:武汉工程大学,2010:4.]

[7]Peng Guangxiong,Li Jing,He Yuhua,et al.Extracting Land Cover Information from CBERS-2’s CCD Image Using Texture Analysis[J].Remote Sensing Technology and Application.2007,22(01):8-13.[彭光雄,李京,何宇华,等.利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息[J].遥感技术与应用,2007,22(01):8-13.]

[8]Puissant A,Hirsch J,Weber C.The Utility of Texture Analysis to Improve Per-pixel Classification for High to Very High Spatial Resolution Imagery[J].International Journal of Remote Sensing,2005,26(4):733-745.

[9]Huang Yan,Zhang Chao,Su Wei,et al.A Study of Optimal Scale Texture Analysis for Remote Sensing Image Classification[J].Remote Sensing for Land &Resources,2008,78(4):14-17,105,109.[黄艳,张超,苏伟,等.合理尺度纹理分析遥感影像分类方法研究[J].国土资源遥感,2008,78(4):14-17,105,109.]

[10]Bao Haiying,Li Yan,Zhao Ping.The Research of Object2oriented Classif ication Method in Remote Sensing Image with Texture Analysis——Taking Yangling County of Shanxi Province as an Example[J].Remote Sensing Information,2009,(4):33-37.[鲍海英,李艳,赵萍.辅以纹理特征的面向对象的遥感影像分类方法研究——以陕西省杨陵县为例[J].遥感信息,2009,(4):33-37.]

[11]Wang Haijun,Le Chengfeng.Extraction of Paddy Field Using Objects-Oriented Fuzzy Classification Approach based on Texture Characteristic[J].Geography and Geo-information Science,2008,24(5):40-43.[王海君,乐成峰.应用基于纹理的面向对象分类模糊方法提取水田信息[J].地理与地理信息科学,2008,24(5):40-43.]

[12]National Remote Sensing Center of China.Introduction of KZ-1[EB/OL].http://www.nrscc.gov.cn/nrscc/kzyh/index.html.2014-8-14.[国家遥感中心.快舟一号卫星简介[EB/OL].http://www.nrscc.gov.cn/nrscc/kzyh/index.html.2014-8-14.]

[13]Baidu Wikipedia.Introduction of Landsat-8 Parameter[EB/OL].http://baike.baidu.com/view/10102539.htm?fr=aladdin.2014-6-27.[百度百科.Landsatt-8卫星参数简介[EB/OL].http://baike.baidu.com/view/10102539.htm?fr=aladdin.2014-6-27.]

[14]Zhu Junjie,Du Xiaoping,Fan Xiangtao,et al.A Advanced Multi-scale Fractal Net Evolution Approach[J].Remote Sensing Technology and Application,2014,29(2):324-329.[朱俊杰,杜小平,范湘涛,等.一种改进的多尺度分形网络演化分割方法[J].遥感技术与应用,2014,29(2):324-329.]

[15]Haralick R M,Shanmugam K,Dinstein I H.Textural features for image classification[J].IEEE Transactions on Systems,Man and Cybernetics,1973,(6):610-621.

[16]Zhang Ce,Zang Shuying,Jin Zhu,et al.Remote Sensing Classification for Zhalong Wetlands based on Support Vector Machine[J].Wetland Science,2011,9(3):263-269.[张策,臧淑英,金竺,等.基于支持向量机的扎龙湿地遥感分类研究[J].湿地科学,2011,9(3):263-269.]

[1] 韩涛,潘剑君,张培育,曹罗丹. Sentinel-2A与Landsat-8影像在油菜识别中的差异性研究[J]. 遥感技术与应用, 2018, 33(5): 890-899.
[2] 钟函笑,边金虎,李爱农. Landsat-8 OLI与Sentinel-2 MSI山区遥感影像辐射一致性研究[J]. 遥感技术与应用, 2018, 33(3): 428-438.
[3] 李珊珊,蒋耿明. 基于通用分裂窗算法和Landsat-8数据的地表温度反演研究[J]. 遥感技术与应用, 2018, 33(2): 284-295.
[4] 杨朦朦,汪汇兵,欧阳斯达,范奎奎,戚凯丽. 基于双树复小波分解的BP神经网络遥感影像分类[J]. 遥感技术与应用, 2018, 33(2): 313-320.
[5] 王苏芸,孙中昶,郭华东,申维. 基于面向对象的东营市城乡建设用地信息提取[J]. 遥感技术与应用, 2017, 32(4): 780-786.
[6] 郝泷,陈永富,刘华,朱雪林,达哇扎西,李伟娜. 基于纹理信息CART决策树的林芝县森林植被面向对象分类[J]. 遥感技术与应用, 2017, 32(2): 386-394.
[7] 王守志,邢立新,仲波,杨爱霞,张福坤,梁敏. 基于Landsat-8 OLI和GF-1 PMS数据融合的铁染蚀变信息提取[J]. 遥感技术与应用, 2016, 31(5): 950-957.
[8] 翟玮,沈焕锋,黄春林. 结合PolSAR影像纹理特征分析提取倒塌建筑物[J]. 遥感技术与应用, 2016, 31(5): 975-982.
[9] 邓滢,张红,王超,刘萌. 结合纹理与极化分解的面向对象极化SAR水体提取方法[J]. 遥感技术与应用, 2016, 31(4): 714-723.
[10] 卢业伟,李强子,杜鑫,王红岩,刘吉磊. 基于高分辨率影像的近海养殖区的一种自动提取方法[J]. 遥感技术与应用, 2015, 30(3): 486-494.
[11] 周艳飞,张绘芳,李霞,杨帆,丁程锋. 基于高分辨遥感数据的胡杨与柽柳树冠提取[J]. 遥感技术与应用, 2015, 30(3): 510-517.
[12] 化蕾,黄洪宇,陈崇成,黄淑华.  基于激光点云数据的客家土楼三维建模[J]. 遥感技术与应用, 2015, 30(1): 115-122.
[13] 邹亚荣,黄磊,张治平. 结合纹理特征的SVM岛礁信息提取分析[J]. 遥感技术与应用, 2014, 29(5): 812-817.
[14] 郭钇宏,王博,刘勇,杨亦宁 . 综合优度法和不一致性法的最优分割参数选择方法[J]. 遥感技术与应用, 2014, 29(3): 489-497.
[15] 刘萌萌,刘亚岚,孙国庆,彭立. 结合纹理特征的SVM样本分层土地覆盖分类[J]. 遥感技术与应用, 2014, 29(2): 315-323.