面向对象的土地覆盖信息提取方法研究及应用  

Research on Object-Oriented Land Cover Information Extraction

作　　者：牟凤云[1] 罗丹[1] 官冬杰[1] 吴晓春[2] 

机构地区：[1]重庆交通大学河海学院,重庆400074 [2]国家测绘地理信息局陕西基础地理信息中心,陕西西安710054

出　　处：《重庆交通大学学报（自然科学版）》2014年第6期104-108,160,共6页Journal of Chongqing Jiaotong University(Natural Science)

基　　金：国家自然科学基金项目(41201546);国家科技支撑计划课题(2012BAH2BB04);重庆交通大学2013年研究生教育创新基金项目(20130101)

摘　　要：以辽宁省沈阳市Landsat-5 TM影像为数据源,利用ERDAS和e Cognition软件分别使用监督分类和面向对象分类方法对试验区土地覆被进行分类。在面向对象分类中选用多尺度分割法、最邻近分类法。分类完成后,计算监督分类误差矩阵得到总体精度90.65%、Kappa系数0.847 8以及生产精度和用户精度,在e Cognition中选用最佳分类结果和分类稳定性统计法得到图表形式的精度结果,最后得到精度结果对比(监督分类/面向对象):聚落91.14%/93.50%,农田86.91%/93.80%,森林91.73%/96.70%,草地84.44%/91.36%,水体98.16%/96.18%。通过精度对比分析得出基于对象的面向对象分类法较于传统的监督分类法提高了分类效率和精度。Taken Landsat-5 TM image in Shenyang city,Liaoning province as a data source,ERDAS software was used for supervised classification and e Cognition software for object-oriented classification. Multi-scale segmentation method in object-oriented classification and the nearest neighbor classification were selected to classify. After classification,the error matrix of supervised classification was calculated to obtain overall accuracy,kappa coefficient,producer accuracy and user accuracy. The best classification result and classification stability method were selected to assess accuracy in e Cognition software. The results were（ supervised classification / object-oriented classification） ： settlement 91. 14% /93. 50%,farmland 86. 91% /93. 80%,forest91. 73% /96. 70%,grassland 84. 44% /91. 36%,water 98. 16% /96. 18%. The result of object-oriented classification method improves the efficiency and accuracy of classification compared to traditional supervised classification method.

关 键 词：土地覆被 面向对象 TM影像 多尺度分割 最邻近算法 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]