Land Cover Classification of Remotely Sensed Imagery UsingMultiple-point Geostatistics
-
摘要: 目的 提出了一种基于多点地统计学理论的遥感影像分类后处理方法。此方法从训练图像中提取先验的空间结构信息,推断类别的空间分布模式和相关关系,训练图像中能够建立包含空间关系的模型,比传统变异函数模型所表达的点对之间的关系更为丰富。将此方法应用于从Landsat TM影像中提取湿地类别,与空间平滑法和基于马尔科夫随机场的分类方法相比,其总体分类精度有所提高,且对曲线分布的地物类别的处理具有明显优势。Abstract: Objective A post-processing method is proposed based on the theory of multiple-point geostatistics.The method extracts prior spatial structures from a training image,and infers the pattern distributionand correlation of classes.A spatial correlation model can be established from training image,which ispreferable to the traditional two-point-based variogram model.An experiment was performed on aLandsat TM image,wetlands with a complicated distribution were extracted.The method was com-pared to the spatial filtering and the contextual Markov random field(MRF)classifier.This approachincreases overall classification accuracy,and has advantages when dealing with classes that have curvi-linear distributions.
-
计量
- 文章访问数: 1577
- HTML全文浏览量: 67
- PDF下载量: 623
下载:
