基于地理加权的k-NN高分辨率遥感影像分类算法改进  

The Modified k-NN Classifier for High Spatial Resolution Remote Sensing Images based on Geographical Weighted Models

作　　者：靳志宾[1] 蒲英霞[1] 陈刚[1] 王结臣[1] 马劲松[1] 杨萌萌[1] 

机构地区：[1]南京大学地理与海洋科学学院,江苏南京210093

出　　处：《遥感技术与应用》2013年第1期97-102,共6页Remote Sensing Technology and Application

基　　金：国家自然科学基金项目(40601074);江苏高校优势学科建设工程项目(PAPD)

摘　　要：与中低分辨率相比,高分辨率遥感影像的信息比较丰富,在使用常规k-NN分类方法基于像元进行高分辨率遥感影像分类时会产生大量的"椒盐噪声"和地物类别错分。根据地理学第一定律,引入地统计模型,将地理权重加入到常规k-NN分类方法中,形成新的地理权重k-NN分类器(Geographically Weighted k-NN,GWk-NN)。该方法首先通过条件概率函数计算出训练样本数据的空间分布特征,然后通过地统计模型对空间分布特征进行拟合,为每种地物选择合适的权重模型,这样既保留了遥感影像中地物的光谱特征,又融入了地物的空间特征,在一定程度上减少甚至消除了"椒盐噪声",提高了分类精度。GWk-NN和常规k-NN分类器分析对比表明:GWk-NN分类方法提高了高分辨率影像的分类精度。k-NN classifier has been widely used in remote sensing image classification due to its simple con- cept and easy implementation. However, it may produce a large amount of ＂salt and pepper＂ noise and wrong classification results in high resolution remote sensing classification because of its rich texture infor- mation. According to the first law of geography,this paper attempts to present a new geographically weigh- ted k-NN classification method （GWk-NN） to solve these problems by incorporating geographical statisti- cal models into the traditional k-NN ciassifier. First of all, the spatial distribution characteristics of the training samples of each land cover class have been calculated through conditional probability function;Sec- ondly,two kinds of geographical statistical models （exponential and Gaussian model） are fitted and the suitable weighting model for each land cover is selected by the least residual error. Finally, a subregion of Nanjing city （SPOT5,2.5 m spatial resolution） is taken as an example to illustrate the validation of GWk- NN method. By comparing the classification results of GWk-NN and k-NN, the study finds that the new GWk-NN classifier can reduce or even eliminate the ＂salt and pepper noise＂ and eventually improve the classification accuracy by making use of spatial and spectral signature of the remote sensing images.

关 键 词：K-NN 空间特征 地理加权模型 GWk-NN 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]