| 基于面向对象分类方法在SPOT影像中的地物信息提取 |
| 投稿时间：2010-10-24 点此下载全文 |
| 引用本文：祖 琪,袁希平,莫源富,袁 磊.基于面向对象分类方法在SPOT影像中的地物信息提取[J].中国岩溶,2011,30(2):227-232. |
| 摘要点击次数: 2247 |
| 全文下载次数: 3433 |
| 学科分类: |
|
| 基金项目:中国地质科学院岩溶地质研究所基本科研业务费项目(2009016) |
|
| 中文摘要:利用基于面向对象分类方法的eCognition软件,以桂林寨底地区为研究区,对影像中各类地物设置不同的分割参数,即初始分割尺度为30,形状因子为0.1,光谱因子为0.9,紧凑度为0.7,光滑度为0.3,能够比较准确地分割出水体、植被、非植被3类地物。根据建立的类层次结构,继续对植被和非植被2个大类进行细分,结果表明当分别选定分割尺度为80和50时效果较理想。利用eCogni-tion对完成分割的地类进行分类,并结合最后的手动修改,取得了较高的分类精度,即总的分类精度达到96.28%,Kappa系数为0.9523。与传统的分类方法进行对比,面向对象分类方法在高分辨率影像分类工作中具有较大的优势。 |
| 中文关键词:eCognition 面向对象分类 类层次结构 分割 最大似然法分类 |
| |
| Surface features’ information extraction from SPOT images with object-oriented classification method |
|
|
| Abstract:With eCognition software of the object-oriented classification method, different segmentation parameters for each surface features in the images is set in the study area of Zhaidi, Guilin. When initial segmentation parameter is 30, shape is 0.1, color is 0.9, compactness is 0.7 and smoothness is 0.3, vegetation, non-vegetation and water body can be parted accurately. Further separation for vegetation and non-vegetation according to the established classification hierarchy, it is concluded that the results close to ideal if the selected segmentation scale is 80 and 50. Classification to the surface features that have been cut by means of eCognition and manually modification has resulted in relatively high accuracy – the general accuracy up to 96.28% and the Kappa coefficient 95.23%. Contrasting with the result by traditional way, the object-oriented classification method is of greater advantage in classifying high-resolution remote sensing data. |
| keywords:eCognition object-oriented classification class hierarchy structure segmentation maximum likelihood classification |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|