面向对象方法在SPOT5影像土地分类中的应用——以京杭大运河南旺地区为例  

Application of Object-oriented Approach in the Spot5 Image Land Classification

作　　者：朱春华[1] 聂跃平[1] 

机构地区：[1]中国科学院遥感应用研究所,北京100101

出　　处：《安徽农业科学》2009年第7期3122-3125,共4页Journal of Anhui Agricultural Sciences

基　　金：国家科技支撑计划资助(2006BAK30B01)

摘　　要：结合京杭大运河山东地区SPOT全色和多光谱融合后的遥感数据,应用面向对象分类法对其进行地物分类,并和传统的基于像元的分类方法进行结果对比分析。结果表明,该方法速度快、精度高、效果好,可以满足对京杭大运河保护规划监测的需求。Combining with the remote sensing data of Beijing-Hangzhou Grand Canal in Shandong fused by multi-spectral and panchromatic SPOT5 data, the ground objects were classified by using object-oriented approach.And it was compared with the results by using the traditional pixel-oriented classification methods. The results indicated that the approach had a higher accuracy, efficiency and effect and it could meet the demands of the protection, layout and detection of Beijing-Hangzhou Grand Canal.

关 键 词：SPOT5影像 遥感分类 面向对象 京杭大运河 

分 类 号：S127[农业科学—农业基础科学]