Please wait a minute...
img

官方微信

遥感技术与应用  2008, Vol. 23 Issue (4): 398-404    DOI: 10.11873/j.issn.1004-0323.2008.4.398
技术研究与图像处理     
新疆干旱区绿洲土壤盐渍化信息提取对比研究
张飞1,2,3,塔西甫拉提•特依拜1,2,丁建丽1,2,依力亚斯江•努尔麦麦提1,2,田源1,2
(1.新疆大学资源与环境科学学院,新疆 乌鲁木齐 830046; 2.新疆大学绿洲生态教育部重点实验室,新疆 乌鲁木齐 830046;3.新疆大学研究生院招生办,新疆 乌鲁木齐 830046)
Contrast Study on Extracting of Soil Salinization in Arid Area of Xinjiang Oasis
ZHANG Fei 1,2,3,Tashpolat•Tiyip 1,2,DING Jian-li 1,2,Ilyas.Nurmuhammat 1,2,TIAN Yuan 1,2
(1.College of Resources and Environment Science,Xinjiang University Urumqi,Urumqi 830046,China;2.Key Laboratory of Oasis Ecology,Xinjiang University Urumqi,Urumqi 830046,China|3.Graduate school of Xinjiang University with Academic Degrees Committee,Urumqi 830046,China)
 全文: PDF(2304 KB)  
摘要:

在遥感影像分类的过程中非光谱特征起着重要的辅助作用。纹理特征作为一种重要的非光谱特征对于遥感影像分类精度的提高也有很重要的作用。以渭干河—库车河三角洲绿洲为例,利用ETM+数据,探讨了该绿洲盐渍化土地覆盖信息的提取方法。提出了基于SVM的光谱和纹理两种信息复合的分类方法,通过此方法对该绿洲进行分类研究,并将分类结果与最小距离法、最大似然法(MLC)、神经网络法(Neural net)和单源数据(光谱)SVM分类结果进行定性和定量比较分析。研究结果表明:该方法能够有效地解决单数据源分类效果破碎、分类精度不高等问题,并对高维输入向量具有较高的推广能力。总精度达到93.179 5%,比单源信息的SVM分类法提高了3.161 8%,比最大似然法提高了4.825 2%,比神经网络法提高了7.475 6%,而与最小距离法相比,总精度甚至提高了11.102 9%,取得了良好的效果。与传统的分类方法的比较表明,文中所提出的分类方法具有明显的优越性和良好的前景,因此该方法更适合于遥感图像分类和盐渍化信息提取,是地物遥感信息提取的有效途径。

关键词: 支持向量机(SVM)盐渍化 灰度共生矩阵 纹理信息    
Abstract:

The non-spectral characteristics play an important role in assisting the image classification in remote sensing,as these characteristics can avoid the mistake classification made by the "the same object with different spectrum" phenomenon.The texture characteristic is one kind non-spectral characteristic.It is also helpful to improve the classification precision.In this paper,the author takes the Delta Oasis of Weigan and Kuqa rivers for example,using ETM+ data; discussing the method of extracting of soil salinization.This paper reports the classification method based on support vector machine(SVM),and introduced the fundamental theory of SVM algorithm,then incorporating of spectrum and texture information.The classification result is compared with minimum distance classification,maximum likelihood classification,neural net classification and single data source(spectrum)SVM classification qualitatively and quantitatively.The research result shows that this method can effectively solve the problem of low accuracy and fracture classification result in single data source classification,it has high spread ability toward higher array input,the overall accuracy is 93.1795%,which increases by 3.1618% comparing with single data source SVM and increases by 4.8252% comparing with maximum likelihood classification,and increase by 7.4756% comparing with neural net classification,even increases by 11.1029% comparing wit minimum distance classification and thus acquires good effectiveness.The classification results were easier interpreted when compared with the conventional classification method.Therefore,the classification method based on SVM(Support Vector Machine)and incorporate the spectrum and texture information can be adapted to RS image classification and monitoring of soil salinization,furthermore,provides and effectives way for the things remote sensing information extraction.

Key words: Support vector machines(SVM)    Soil salinization    Gray co-occurrence matrix    Texture information
收稿日期: 2008-01-16 出版日期: 2011-11-03
:  TP 79  
基金资助:

自治区高校科研计划项目(XJEDU2004I06,XJEDU2005I07);教育厅创新研究群体基金项目(XJEDU2004G04);新疆绿洲重点实验室开放课题(XJDX0201-2007-01,03);新疆大学青年科研启动基金。

作者简介: 张飞(1980- ),男,硕士研究生,主要从事遥感技术的理论和应用研究。E-mail:zhangfei3s@yahoo.com.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  

引用本文:

张飞,塔西甫拉提?特依拜,丁建丽,依力亚斯江.努尔麦麦提,田源. 新疆干旱区绿洲土壤盐渍化信息提取对比研究[J]. 遥感技术与应用, 2008, 23(4): 398-404.

ZHANG Fei,Tashpolat?Tiyip,DING Jian-li,Ilyas.Nurmuhammat,TIAN Yuan. Contrast Study on Extracting of Soil Salinization in Arid Area of Xinjiang Oasis. Remote Sensing Technology and Application, 2008, 23(4): 398-404.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2008.4.398        http://www.rsta.ac.cn/CN/Y2008/V23/I4/398

[1] Liu Y H,Niu Z.Regional Land Cover Image Classification and Accuracy Evaluation Using MODIS Data[J].Remote Sensing Technology and Application,2004,19(5):217-224.[刘勇洪,牛铮.基于MODIS遥感数据的宏观土地覆盖特征分类方法与精度分析研究[J].遥感技术与应用,2004,19(5):217-224.]
[2] Metternicht G I,Zinck J A.Remote Sensing of Soil Salinity Potentials and Constraints[J].Remote Sensing of Environment,2003,85:1-20.
[3] Liu C M,Zhang L J,Davis C J,et al.Comparison of Neural Net Works and Statistical Methods in Classification of Ecological Habitats Using FIA Data[J].Forest Science,2003,49(4):619-631.
[4] Zhang X G.Introduction to Statistical Learning Theory and Support Vector Machines[J].Acta Automatica Sinica,2000,26(1):32-42.[张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.]
[5] Huang H P,Liu Y H.Fuzzy Support Vector Machines for Pattern Recognition and Data Mining[J].International Journal of Fuzzy Systems,2002,4(3):826-835.
[6] He X,Liu C Q.Text-independent Speaker Identification Based on Support Vector Machines [ J]. Computer Engineering,2000,26(6):61-63.[何昕,刘重庆.基于支撑向量机的文本无关的说话人识别系统[J].计算机工程,2000,26(6):61-63.]
[7] Muller K R.An Introduction to Kernel-Based Learning Algorithms[J].IEEE Transactions on Neural Networks,2001,12(2):181-201.
[8] Rolif,Fumira G.Support Vector Machines for Remote Sensing Image Classification[EB/OL]. http://citeseer. nj. nec.com,2004-09-12.
[9] Yan M C,Zhang Y J,Bao Y S.Deriving Bamboos from IKONOS Image by Texture Information[J].Remote Sensing Information,2004,2:30-34.[颜梅春,张友静,鲍艳松.基于灰度共生矩阵法的IKONOS影像中竹林信息提取[J].遥感信息,2004,2:30-34.]
[10] Sun X F,Lu J,Sun X D.Extraction of Green Space in Urban High Resolution Remote Sensing Image[J].Remote Sensing Technology and Application,2006,21(2):159-162.[孙小芳,卢健,孙小丹.城市地区高分辨率遥感影像绿地提取研究[J].遥感技术与应用,2006,21(2):159-162.]
[11] Zhao P,Fu Y F,Zheng L G,etal.Cart-based Land Use/Cover Classification of Remote Sensing Images[J].Journal of Remote Sensing,2005,9(6):708-715.[赵萍,傅云飞,郑刘根,等.基于分类回归树分析的遥感影像土地利用/覆被分类研究[J].遥感学报,2005,9(6):708-715.]
[12] Zhang J S,He C Y,Pan Y Z,et al.The High Spatial Resolution RS Image Classification Based on SVM Method with the Multi-Source Data[J].Journal of Remote Sensing,2006,10(1):49-57.[张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006,10(1):49-57.]
[13] Zhou T G,Guo D Z,Sheng Y H.A Study of Texture and Description for Multi-band Remote Sensing Image Based on The Gray Vector [J]. Journal of Xi ' an University of Science &Technology,2000,20(4):336-338.[周廷刚,郭达志,盛业华.灰度矢量多波段遥感影像纹理特征及其描述[J].西安科技学院学报,2000,20(4):336-338.]
[14] Yang S Y,Hu J,Cao Z L.Object Recognition System Based on Image Texture Analysis[J].Journal of Tianjin Institute of Technology,2001,17(4):31-33.[杨淑莹,胡军,曹作良.基于图像纹理分析的目标物体识别方法[J].天津理工学院学报,2001,17(4):31-33.]
[15] Xue C S,Wang X.Methodology and Application of Remote Sensing Image Analysis Based on Fractal Geometry[J].Geological Science and Technology Information,1997,16:99-105.[薛重生,王霞.基于分形几何的遥感图像纹理分析方法及应用[J].地质科技情报,1997,16 :99-105.]
[16] Haralick R M,Shanmugan K,Dinsrein I.Textural Features for Image Classification[J].IEEE Trans.Syst.Man Cybern,1973,6:610-621.
[17] Peng G X,Li J,He Y h,et al.Extracting Land Cover Information from CBERS-2's CCD Image Using Texture Analysis[J].Remote Sensing Technology and Application,,2007,22(1):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(1):8-13.]
[18] Zhang J S,He C Y,Pan Y Z,et al.The High Spatial Resolution RS Image Classification Based on SVM Method with the Multi-Source Data[J].Journal of Remote Sensing,2006,10(1):49-57.[张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006,10(1):49-57.]
[19] Zhang Y J,Gao Y X Huang H,et al.Research on Remote Sensing Classification of Urban Vegetation Species Based on SVM Decision-making Tree[J].Journal of Remote Sensing,2006,10(2):191-196.[张友静,高云霄,黄浩,等.基于SVM决策支持树的城市植被类型遥感分类研究[J].遥感学报,2006,10(2):191-196.]
[20] Li P C,Xu S H.Support Vector Machine and Kernel Function Characteristic Analysis in Pattern Recognition[J].Computer Engineering and Design,2005,26(2):302-304.[李盼池,许少华.支持向量在模式识别中的核函数特性分析[J].计算机工程与设计,2005,26(2):302-304.]
[21] Kerrthi S S,Lin C I.Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel [J]. Neural Computation,2003,15(7):1667-1689.
[22] Ilyas·Nurmuhammat,Ding J L,Tashpolat·Tiyip,et al.Soil Salinization Monitoring Based on Support Vector Machine Classification[J].Research of Soil and Water Conservation,2007,14(4):209-214,222.[依力亚斯江·努尔麦麦提,丁建丽,塔西甫拉提·特依拜,等.基于支持向量机分类的遥感土壤盐渍化信息监测[J].水土保持研究,2007,14(4):209-214,222.]
[23] Gong P,Marceau D J,Howarth P J.A Comparison of Spatial Feature Extraction Algorithms for Land-use Classification with SPOT HRV Data[J].Remote Sensing of Environment,1992,40:137-151.
[24] Dwivedi R S,Rao B R M.The Selection of the Best Possible Landsat TM Band Combination for Delineating Salt-affected Soils[J].International Journal of Remote Sensing,1992,13(11):2051-2058.
[25] Qian Y,Hao Y L.Oasis of Xinjiang[M].Urumqi:Xinjiang People Press, 2000, 5: 358-359. [钱云,郝毓灵.新疆绿洲[M].乌鲁木齐:新疆人民出版社,2000,5:358-359.]

[1] 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.
[2] 赵玉,王红,张珍珍. 基于遥感光谱和空间变量随机森林的黄河三角洲刺槐林健康等级分类[J]. 遥感技术与应用, 2016, 31(2): 359-367.
[3] 林志垒,晏路明. 高光谱影像的BDT-SVM地物分类算法与应用[J]. 遥感技术与应用, 2016, 31(1): 177-185.
[4] 郝利娜,张志,张翠芬. 山东省寿光市滨海地区盐田信息提取方法研究[J]. 遥感技术与应用, 2013, 28(3): 526-532.
[5] 徐 佳,陈媛媛,黄其欢,何秀凤. 综合灰度与纹理特征的高分辨率星载SAR图像建筑区提取方法研究[J]. 遥感技术与应用, 2012, 27(5): 692-698.
[6] 宋翠玉,李培军,杨锋杰. 基于多元局部二值模式的遥感图像纹理提取与分类[J]. 遥感技术与应用, 2011, 26(3): 322-327.
[7] 邵晓敏, 刘勇. 基于纹理的乌兰布和沙漠地区植被信息提取[J]. 遥感技术与应用, 2010, 25(5): 687-694.
[8] 傅文杰, 林明森. 利用SVM与灰度共生矩阵从QuickBird 影像中提取枇杷信息[J]. 遥感技术与应用, 2010, 25(5): 695-699.
[9] 阿依提拉·吾加布都拉, 塔西甫拉提·特依拜, 古丽加玛丽·吾不力. 基于面向对象方法的遥感土壤盐渍化信息监测——以渭干河—库车河三角洲绿洲为例[J]. 遥感技术与应用, 2010, 25(3): 373-378.
[10] 刘廷祥,黄丽梅,鲍文东. 基于CBERS-02B和SPOT-5全色波段的图像融合纹理信息评价研究[J]. 遥感技术与应用, 2009, 24(1): 103-108.
[11] 汤井田,胡丹,龚智敏. 基于SVM的SAR图像分类研究[J]. 遥感技术与应用, 2008, 23(3): 341-345.
[12] 邹斌, 张腊梅, 裴彩红, 张晔. 基于SVM的POL-SAR图像分类研究[J]. 遥感技术与应用, 2007, 22(5): 633-636.
[13] 彭光雄,李 京,何宇华,胡德勇. 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(1): 8-13.
[14] 张红,王振会,许建明,裴晓芳 . 可见光云图日食阴影订正效果的纹理特征量分析[J]. 遥感技术与应用, 2004, 19(1): 47-51.
[15] 白香花,刘素红,唐世浩,朱启疆,帅艳民. 基于纹理分析的去噪声方法研究[J]. 遥感技术与应用, 2003, 18(1): 36-40.