遥感影像土地覆盖分类的多点地统计学方法

Land Cover Classification of Remotely Sensed Imagery Using Multiple-point Geostatistics

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。

A post-processing method is proposed based on the theory of multiple-point geostatisties. The method extracts prior spatial structures from a training image, and infers the pattern distribution and correlation of classes. A spatial correlation model can be established from training image, which is preferable to the traditional two-point-based variogram model. An experiment was performed on a Landsat 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 approach increases overall classification accuracy, and has advantages when dealing with classes that have curvi- linear distributions.