Please wait a minute...
img

官方微信

遥感技术与应用  2010, Vol. 25 Issue (4): 540-546    DOI: 10.11873/j.issn.1004-0323.2010.4.540
图像处理     
基于变差函数纹理和BP人工神经网络的QuickBird影像分类研究

马友平
湖北民族学院生物科学与技术学院,湖北 恩施 445000
The Classification Research of QuickBird Image Based on Variogram Texture and BP Artificial Neural Networks
MA You-Ping
School of Biological Science and Technology,Hubei Institute for Nationalities,Enshi 445000,China
 全文: PDF(5902 KB)  
摘要:

通过对QuickBird影像的主成分分析,发现第一主成分信息量为67.09%,第二主成分信息量为31.73%,合计98.81%,因此选了第一、第二主成分进行纹理提取。纹理提取时采用绝对变差函数纹理,窗口大小为3×3,步长为1。地物类型分为4类即建筑物、水体、植被和裸地。BP人工神经网络的拓扑结构为4-4-1,隐层传递函数为S函数(logsig),输出层传递函数为线性(purelin),训练函数为Trainscg;应用该神经网络结构分别对QuickBird影像的多光谱影像和一二主成分及一二主成分纹理影像进行了分类,分别算出了前者的P=84.54%,Kappa系数K=78.50%;后者的P=89.46%,Kappa系数K=85.29%,同时发现加入纹理后分类结果显著提高。

关键词: 变差函数纹理BP人工神经网络QuickBird分类    
Abstract:

Using the principal component analysis method of QuickBird image obtained the information of the first and the second principal component was 67.09% and 31.73% respectively,totaling 98.82%.Therefore,the first and the second principal component were selected to extract texture.We used the absolute variogram to extract the texture,the window size is 3×3 and the step size is 1.The land type was divides into four types,it is building, water body,vegetation and bare land. The topological structure of BP artificial neural network is 4-4-1,the hidden layer transfer function is S (logsig) and the output layer transfer function is linear function,the training function is Trainscg.Adopted the neural network to classified QuickBird multispectral image and the principal components texture image,also figure out the preceding kind of P=84.54%,Kappa coefficient K=78.50%;later kind of P=89.46% and Kappa coefficient K=85.29%.The results demonstrated that the image classifications were enhanced after texture was added.

Key words: Variogram    Texture    BP artificial neural networks    QuickBird    Classification
出版日期: 2010-10-21
基金资助:

湖北省自然科学基金项目(2008CDB049),湖北民族学院博士基金项目。

作者简介: 马友平(1968-),男,副教授,博士,主要从事3S技术应用研究。E-mail:youpingma@sina.com。
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  
马友平

引用本文:

马友平. 基于变差函数纹理和BP人工神经网络的QuickBird影像分类研究[J]. 遥感技术与应用, 2010, 25(4): 540-546.

MA You-ping. The Classification Research of QuickBird Image Based on Variogram Texture and BP Artificial Neural Networks. Remote Sensing Technology and Application, 2010, 25(4): 540-546.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2010.4.540        http://www.rsta.ac.cn/CN/Y2010/V25/I4/540

[1]Song Tiequn.Analysis of Remote Sensing Image Texture Bas-ed on MATLAB[J].Geomatics & Spatial Information Technology,2009,32(2):71-74.[宋铁群.基于MATLAB的遥感影像纹理特征分析[J].测绘与空间地理信息,2009,32(2):71-74.]
[2]Li Xiaotao.Statistics and Neural Network in Remote Sensing Phantom Classification Applied Research[D].Shandong Scientific and Technical University Masters Degree Paper,2004.[李小涛.地统计学和神经网络在遥感影像分类中的应用研究[D].山东科技大学硕士学位论文,2004.]
[3]Guo Dejun,Song Zhecun.A Study on Texture Image Classifying Based on Gray-level Co-occurrence Matrix[J].Forestry Machinery & Woodworking Equipment,2005,33(7):21-23.[郭德军,宋蛰存.基于灰度共生矩阵的纹理图像分类研究[J].林业机械与木工设备,2005,33(7):21-23.]
[4]Li Peijun,Li Zhengxiao.Comparison of Three Geostatistical Texture Measures for Remotely Sensed Data Classification[J].Geography and Geo-information Science,2003,19(4):89-92.[李培军,李争晓.三种地统计学图像纹理用于遥感图像分类的比较[J].地理与地理信息科学,2003,19(4): 89-92.]
[5]Miranda F P,Cart J  P.Application of the Semivariogram Textural Classifier(STC) for Vegetation Discrimination Using SIR-B Data of the Guiana Shield,Northwestern Brazil[J].Remote Sensing Reviews,1994,10:155-168.
[6]Chica-Olmo M,Arbarea-Hemandez F.Computing Geostatistical Image Texture for Remotely Sensed Data Classification[J].Computers & Geosciences,2000,26(4):373-383.
[7]Pei Liang,Tan Yang,Li Wenjie.The Classification of Remote Sensing Image Based on Variogram and the Neural Network[J].Remote Sensing Information,2009,(1):60-65.[裴亮,谭阳,李文杰.基于变差函数和神经网络的遥感影像分类[J].遥感信息,2009,(1):60-65.]
[8]Zhang Guangbao.The Application of Artificial Neural Network to Classification Processing of Remote Sensing Digital Images[J].Remote Sensing for Land & Resources,2003,(1):16-18.[张光宝.人工神经网络在遥感数字图像分类处理中的应用[J].国土资源遥感,2003,(1):16-18.]
[9]Wang Zhengquan.Statistics and in Ecology Application[M].Beijing:Scientific Publishing House,1999:l-102.[王政权.地统计学及在生态学中的应用[M].北京:科学出版社,1999:1-102.]
[10]Curran P J.The Semivariogram in Remote Sensing:An Introduction[J].Remote Sensing of Environment,1988,24(3):493-507.
[11]Chu Jialan,Zhang Jie,Wang Xiaolong.Comparison of Extracted Vegetation Information of Dongsha Island from SPOT and QuickBird Images[J].Journal of Marine Sciences,2006,24(2):79-85.[初佳兰,张杰,王小龙.SPOT、QuickBird卫星遥感数据提取东沙岛植被信息的比较[J].海洋学研究,2006,24(2):79-85.]
[12]Zhang Ningyu,Wu Quanyuan.Information Influence on Qui-ckBird Images by Brovey Fusion and Wavelet Fusion[J].Remote Sensing Technology and Application,2006,21(1):67-70.[张宁玉,吴泉源.Brovey融合与小波融合对QuickBird图像的信息量影响[J].遥感技术与应用,2006,21(1):67-70.]

 

[1] 王常颖,田德政,韩园峰,隋毅,初佳兰. 基于属性差决策树的全极化SAR影像海冰分类[J]. 遥感技术与应用, 2018, 33(5): 975-982.
[2] 陈伟民,张凌,宋冬梅,王斌,丁亚雄,许明明,崔建勇. 基于AdaBoost改进随机森林的高光谱图像地物分类方法研究[J]. 遥感技术与应用, 2018, 33(4): 612-620.
[3] 苏阳,祁元,王建华,徐菲楠,张金龙. 基于航空高光谱影像的额济纳绿洲土地覆被提取[J]. 遥感技术与应用, 2018, 33(2): 202-211.
[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] 李想,刘凯,朱远辉,蒙琳,于晨曦,曹晶晶. 基于资源三号影像的红树林物种分类研究[J]. 遥感技术与应用, 2018, 33(2): 360-369.
[6] 江东,陈帅,丁方宇,付晶莹,郝蒙蒙. 基于面向对象的遥感影像分类研究——以河北省柏乡县为例[J]. 遥感技术与应用, 2018, 33(1): 143-150.
[7] 秦俊,冷寒冰,赵广琦,景军,周坚华. 物候和波谱—位置分析在城镇绿化植物群分类中的应用[J]. 遥感技术与应用, 2017, 32(5): 948-957.
[8] 施佩荣,陈永富,刘华,吴云华,魏新,钟泽兵. 基于改进的面向对象遥感影像分类方法研究—以西藏米林县典型林区为例[J]. 遥感技术与应用, 2017, 32(3): 466-474.
[9] 付伟,徐涵秋,王美雅,王帅,胡秀娟,张博博,林中立. 南方红壤典型水土流失区植被分类及植被类型变化的遥感评估—以福建省长汀县河田地区为例[J]. 遥感技术与应用, 2017, 32(3): 546-555.
[10] 朱钟正,陈玉福,朱文泉,郑周涛. 适用于多目标遥感自动解译的最佳专题指数筛选[J]. 遥感技术与应用, 2017, 32(3): 564-574.
[11] 刘远,周买春. 3种IGBP分类系统的土地覆盖数据在韩江流域的对比分析[J]. 遥感技术与应用, 2017, 32(3): 575-584.
[12] 苏红军,赵波. 基于共形几何代数的高光谱遥感波段选择方法[J]. 遥感技术与应用, 2017, 32(3): 539-545.
[13] 史飞飞,高小红,杨灵玉,何林华,贾伟. 基于HJ-1A高光谱遥感数据的湟水流域典型农作物分类研究[J]. 遥感技术与应用, 2017, 32(2): 206-217.
[14] 郝莹莹,罗小波,仲波,杨爱霞. 基于植被分区的中国植被类型分类方法[J]. 遥感技术与应用, 2017, 32(2): 315-323.
[15] 袁春琦,徐佳,程圆娥,陈媛媛,许康. 基于协同训练与集成学习的极化SAR图像半监督分类[J]. 遥感技术与应用, 2017, 32(2): 380-385.