陈丹,武淑琴

• 1:湖北中医药大学管理学院/湖北省人文社会科学重点项目研究基地中医药发展研究中心

摘要(Abstract)：

针对高分辨率遥感影像分类的传统ID3算法采用的信息增益熵为局部非回溯的启发式的缺点,提出了决策树引入模拟退火算法,得到一个面向影像特征优先级的优化的决策树分类算法。采用优化的决策树算法进行高分辨率遥感影像的分类,能较好地解决样本依赖性问题,并且得到一个全局优化的分类结果。通过实验,对农村地区的SPOT影像进行分类,并且通过对较优尺度下优化的决策树算法与神经网络算法和最大似然法对实验区域的影像分类精度的比较,证明了与ID3决策树分类方法相比较,优化的决策树方法能有效地提高农村地区在各尺度下SPOT影像的分类精度。

关键词(KeyWords)： 高分辨率遥感影像;决策树;模拟退火;破碎度

Abstract:

Keywords:

基金项目(Foundation): 湖北省社会科学基金项目([2010]349);; 湖北省人文社会科学重点项目研究基地——中医药发展研究中心项目(ZX2013Y8)

作者(Author): 陈丹,武淑琴

DOI: 10.16251/j.cnki.1009-2307.2016.09.016

参考文献(References)：

• [1]TURNER B,MEYERW B,SKOLE D L.Global Landuse/Land-Coverchange:toward an Integrated Study[J].Am Bio,1994,23(1):91-95.
• [2]NISHII R,EGUCHI S.Supervised image classification by contextual ada boost based on posteriors in neighborhoods[J].IEEE Transaction on Geoscience and Rem ote Sensing,2005,43(11):2547-2554.
• [3]WILKINSOM G G.Results and imp lications of a study of fifteen years of satellite image classification experiments[J].IEEE Transaction on Geoscience and Remote Sensing,2005,43(3):433-440.
• [4]杜凤兰,田庆久,夏学齐,等.面向对象的地物分类法分析与评价[J].遥感技术与应用,2004,19(1):20-23.
• [5]LU D,WENG Q.A survey of image classification methods and techniques for improving classification performance[J].International Journal of Remote Sensing,2007,28(5):823-870.
• [6]FRIEDL M A,BRODLEY C E(1997).Decision tree classification of land cover from remotely sensed data[J],Remote Sensing Environment,1997,61(3):399-409.
• [7]RIEK L,LAWRENCE,ANDREA W.Rule-based classifieation systems using classification and regression tree(CART)Analysis[J].PE&RS,2001,67(10):1137-1142.
• [8]YOSHIKAWA M,SHINDO H,NISHII R.Fully automated design of binary decision tree for land cover classification[C]//Proceedings of the 1995International Geoscience and Remote Sensing Symposium.Part3(of 3),JUL 10-14,1995.
• [9]F S E,STENHOUSE G B,HANSEN M J,et al.An Integrated decision tree Approach(IDTA)to mapping land cover using satellite remote sensing in support of grizzly bear habitat analysis in the Alberta yellow head ecosystem[J].Canadian Journal of Remote Sensing,2001,27:579-592.
• [10]DING Qiang,DING Qin,PERRIZO.Decision tree classification of spatial data Streams using peano count trees[C]//Applied Computing 2002:Proceeedings of the 2002 ACM Symposium on Applied Computing.Mar11-14,2002:413-417.
• [11]DE COLSTOUN,STORY M H,THOMPSON C.Vegetation mapping using multi-temporal ETM+data and a decision tree classifier[C]//2002IEEE International Geoscience and Remote Sensing Symposium(IGARSS2002).Jun24-28,2002:2890-2892.
• [12]潘琛,杜培军,张海荣,决策树分类法及其在遥感图像处理中的应用[J].测绘科学,2008,33(1):208-211.
• [13]罗来平,宫辉力,刘先林,基于决策树算法的遥感图像分类研究与实现[J]计算机应用研究,2007(1):207-209.
• [14]付炜.土壤遥感分类识别推理决策器的设计[J].遥感学报,2001,5(6):434-441.
• [15]韩涛.用TM资料对祁连山部分地区进行针叶林、灌木林分类研究[J],遥感技术与应用,2002,17(6):317-321.
• [16]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(1):17-21.
• [17]QUINLAN J R.Induction of decision trees[J].Machine Learning,1986,1(1):81-106.
• [18]FRIEDL M A,BRODLEY C E,STRAHLER A H.Maximizing and cover classification accuracies produced by decision trees at continental to global scales[J].IEEE Transactions on Geo science and Remote Sensing,1999,37(2):969-977.
• [19]MCIVER D K,FRIEDL M A.Using prior probabilities in decision-tree remotely sensed data[J].Remote Sensing of Environment,2002,81:253-261.
• [20]HANSEN M,DUBAYAH R,DE FRIES R.Classification trees,an alternative to traditional land cover classifiers[J].International Journal of Remote Sensing,1996,17:1075-1081.
• [21]QUINLAN J R.C4.5:programs for machine learning[M].San Mateo.CA:Morgan Kaufm an Publishers,1993.