Adaptive Bayesian contextual classification based on Markov random fields
Adaptive Bayesian contextual classification based on Markov random fields
复制标题
DOI：
10.1109/igarss.2002.1026136
复制
发表时间：
2002-11
期刊：
影响因子：
--
通讯作者：
Q. Jackson;D. Landgrebe
中科院分区：
文献类型：
--
作者：
Q. Jackson;D. Landgrebe
本文提出了一种自适应贝叶斯上下文分类方法，该方法在统计估计和分类中同时利用了光谱和空间像素间的相关性。本质上，该分类器是自适应分类过程和贝叶斯上下文分类过程的建设性耦合。在该分类器中，每个像素及其空间邻居的类的联合先验概率由马尔可夫随机场建模。用真实的高光谱数据进行的实验表明，该分类器在小样本集的情况下，可以达到与大样本集的最大似然分类器相似的分类精度.另外，产生具有显著更少的散斑误差的分类图。
In this paper an adaptive Bayesian contextual classification procedure that utilizes both spectral and spatial interpixel dependency contexts in statistics estimation and classification is proposed. Essentially, this classifier is the constructive coupling of an adaptive classification procedure and a Bayesian contextual classification procedure. In this classifier, the joint prior probabilities of the classes of each pixel and its spatial neighbors are modeled by the Markov random field. Experiments with real hyperspectral data show that, starting with a small training sample set, this classifier can reach classification accuracies similar to that obtained by a pixelwise maximum likelihood classifier with a very large training sample set. Additionally, classification maps are produced which have significantly less speckle error.