高光谱影像信息向量机分类

信息向量机是一种基于贝叶斯理论的稀疏高斯过程方法,其模型训练速度快、内存耗费小、稀疏性强,具有良好的预测性能。本文从高斯过程回归模型出发,提出了一种基于信息向量机的高光谱影像分类方法,针对高斯过程分类中的非高斯噪声模型,采用假定概率滤波算法将分类问题转化为回归问题,通过最大化边缘似然函数进行模型训练,选择活动子集中的信息向量数量达到了稀疏的目的。通过ROSIS影像试验,表明了基于信息向量机的高光谱影像分类方法的优势。

Informative Vector Machine Classification for Hyperspectral Imagery

Informative vector machine is a method of sparse Gaussian process based on Bayesian theory, which has high speed in model training,smal l consuming in memory,strong effective in sparseness and good forecasting performance.In this paper,the Gaussian process regression model is introduced fi rstly, and then a hyperspectral imagery classification method based on informative vector machine is brought forward.Secondly, to solve the problem of non-Gaussian noise model in the Gaussian process classification,the classification problem is transformed into a regression problem by using the assume density fi ltering algorithm,after which model is trained by maximizing the marginal l ikel ihood function. Final ly,the number of informative vector is chosen in active subset to achieve the purpose of sparse. According to the experimental results of ROSIS images,the advantages of hyperspectral imagery classifi-cation method based on informative vector machine are val idated.