基于先验知识的MCMC在混合像元分解中的应用研究

MCMC方法是一种动态的参数估计方法,研究MCMC方法在遥感影像混合像元分解中的应用。传统的混合像元分解一般是基于固定端元的,而实际上影像中像元并不都是由完全相同的端元组成。基于MCMC方法提出了一种端元可变的像元分解算法,并且充分利用了端元的累计先验知识。算法将端元选取和丰度反演合为一个步骤,抽象成一个估计参数的随机过程,在端元数目可变的前提下,基于可逆的跳跃式MCMC方法估计参数。在状态转移过程中,加入端元的累计先验知识,提高算法效率。这种算法不需要人工干预,能够实现自动化像元分解,并且具有较高的精度。结果表明,基于修正MCMC的端元可变的自动化解混算法在分解精度和稳定性方面均优于基于固定端元的混合像元分解方法。

Application of the MCMC in Pixel Unmixing Based on the Priori Knowledge

The MCMC method is a dynamic method for parameter estimation,the application of MCMC in pixel unmixing of remote sensing image was studied.Traditional unmixing methods are based on the fixed endmember,and need to assume that the remote sense image exits pure pixel.In fact,this assumption is not necessarily true,and all pixels are not composed of the same endmembers.The study merges the endmember extration and unmixing into one step,and Abstracts it to a random process.Within the premise of variable number of endmembers,use reversible jump MCMC method to estimate parameters.The accumulated knowledge of endmembers during the state transition process was adopted to improve algorithm efficiency.This algorithms does not require human intervention.It can achieve automated unmixing,and has a high accuracy.The experiments showed that the algorithm based on MCMC is superior to the traditional unmixing method in both accuracy and stability.