[1]翁永玲,等.基于QuickBird数据的输电线路径优选中地表信息提取[J].东南大学学报(自然科学版),2010,40(3):587-592.[doi:10.3969/j.issn.1001-0505.2010.03.029]
 Weng Yongling,Fan Xingwang,Hu Wusheng,et al.Decision tree classification method with QuickBird image applied in electric transmission path design[J].Journal of Southeast University (Natural Science Edition),2010,40(3):587-592.[doi:10.3969/j.issn.1001-0505.2010.03.029]
点击复制

基于QuickBird数据的输电线路径优选中地表信息提取()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
40
期数:
2010年第3期
页码:
587-592
栏目:
测绘与导航
出版日期:
2010-05-20

文章信息/Info

Title:
Decision tree classification method with QuickBird image applied in electric transmission path design
作者:
翁永玲1 2 范兴旺1 胡伍生1 徐君民3 任亚群3
1 东南大学交通学院,南京 210096; 2 中国科学院遥感应用研究所/北京师范大学遥感科学国家重点实验室,北京 100101; 3 江苏省电力设计院, 南京 211102
Author(s):
Weng Yongling12 Fan Xingwang1 Hu Wusheng1 Xu Junmin3 Ren Yaqun3
1 School of Transportation, Southeast University, Nanjing 210096,China
2 State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing 100101, China
3 Electric Design Institution of Jiangsu Province, Nanjing 211102, China
关键词:
QuickBird 决策树分类 纹理 自适应滤波 输电线路径优选
Keywords:
QuickBird decision tree classification texture adaptive filter power path optimization
分类号:
P237
DOI:
10.3969/j.issn.1001-0505.2010.03.029
摘要:
针对输电线路径优选的目标,利用QuickBird数据,基于地物类型光谱特征分析,结合遥感影像的纹理特征,采用决策树分类算法,提取影响输电线路径选择的主要地物要素.研究影响输电线选线的相关要素(如居民区、道路、水体等)及其背景地物要素(如耕地、空地等)的光谱特征和纹理特征,确立以4个波段亮度值、归一化植被指数(NDVI)和纹理对比度参数作为特征变量,建立了基于光谱和纹理组合的决策树分类模型,有效地实现居民地、道路和水体信息的提取,并将自适应滤波方法用于分类后处理,优化了分类结果.总体精度由82.09%提高到 92.83%,Kappa系数由0.760 8提高到0.904 1.该精度能够满足输电线路径初选优化的要求,为提取影响输电线路径初选地物要素提供了高效快速的技术方法和基础地理数据.
Abstract:
With the advancement of remote sensing technology, more and higher spatial resolution data such as QuickBird have been applied in engineering projects. The distribution of residential areas, roads and water bodies should be taken into account when electric transmission paths are designed. Recently,the knowledge based on the interpretation of these images has become an effective and efficient approach to realize the automatic interpretation which can integrate spectral and other associated information such as texture. According to the objects of the electric transmission path design, the decision tree classification method is adopted to extract residential areas, roads and water bodies from QuickBird data. First, relevant variables including the grey values of four bands, NDVI(normalized difference vegetation index)and contrastively textural information are selected and extracted. Then based on the analysis of spectral and textural characteristics, the decision tree model is built. The results of classifications are optimized by using an adaptive filter to reduce speckle while preserving the edges in residential areas and roads. The overall accuracy is improved from 82.09% to 92.83% and the Kappa coefficient increases from 0.760 8 to 0.904 1. The results are satisfied with the electric transmission path design.

参考文献/References:

[1] Bischof H,Schneider W,Pinz A J.Multispectral classification of landsat-images using neural networks [J]. IEEE Transactions on Geoscience and Remote Sensing,1992,30(3):482-490.
[2] Lawrence R L,Andrea W.Rule-based classification systems using classification and regression tree(CART)analysis [J]. Photogrammetric Engineering & Remote Sensing,2001,67(10):1137-1142.
[3] Mciver D K,Friedl M A.Using prior probabilities in decision tree classification of remotely sensed data [J].Remote Sensing of Environment,2002,81(2/3):253-261.
[4] Pal M,Mather P M.An assessment of the effectiveness of decision tree methods for land cover classification [J].Remote Sensing of Environment,2003,86(4):554-565.
[5] 李爽,张二勋.基于决策树的遥感影像分类方法研究 [J].地域研究与开发,2003,22(1):17-21.
  Li Shuang,Zhang Erxun.The decision tree classification and its application in land cover [J].Areal Research and Development,2003,22(1):17-21.
[6] 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):708-716.
  Zhao Ping,Fu Yunfei,Zheng Liugeng,et al.Satyanarayana B.Cart-based land use/cover classification of remote sensing images [J].Journal of Remote Sensing,2005,9(6):708-716.(in Chinese)
[7] Wang Le,Sousa W P,Gong P,et al.Comparison of IKONOS and QuickBird images for mapping mangrove species on the Caribbean coast of Panama [J].Remote Sensing of Environment,2004,91(3/4):432-440.
[8] Anys H,He D C.Evaluation of textural and multipolarization radar features for crop classification [J]. IEEE Transactions on Geoscience and Remote Sensing,1995,33(5):1170-1181.
[9] Narasimha R P V,Sesha S M V R,Sreenivas K,et a1.Textural analysis of IRS-1D panchromatic data for land cover classification [J].International Journal of Remote Sensing,2002,23(17):3327-3345.
[10] Franklin S E,Wulder M A,Gerylo G R.Texture analysis of IKONOS panchromatic data for Douglas-fir forest age class separability in British Columbia [J].International Journal of Remote Sensing,2001,22(13):2627-2632.
[11] Haralick R M,Shanmuga K,Dinstein I.Textural features for image classification [J]. IEEE Transactions on Systems Man and Cybernetics,1973,3(6):610-621.
[12] Clausi D A.An analysis of co-occurrence texture statistics as a function of grey level quantization [J].Canadian Journal of Remote Sensing,2002,28(1):45-62.
[13] Shi Zhenghao,Fung K B.A comparison of digital speckle filters[C] //Proceedings of IGRASS 94.Pasadena,USA,1994:2129-2133.

备注/Memo

备注/Memo:
作者简介: 翁永玲(1962—),女,博士,副教授,mgwyl@yahoo.com.cn.
基金项目: 江苏省电力设计院/东南大学科研合作基金资助项目(8521002486)、中国科学院遥感应用研究所/北京师范大学遥感科学国家重点实验室开放研究基金资助项目(2009KFJJ002).
引文格式: 翁永玲,范兴旺,胡伍生,等.基于QuickBird数据的输电线路径优选中地表信息提取[J].东南大学学报:自然科学版,2010,40(3):587-592. [doi:10.3969/j.issn.1001-0505.2010.03.029]
更新日期/Last Update: 2010-05-20