SAR图像小波域隐Markov模型中状态参数的Turbo迭代估计

利用小波域隐Markov模型能够有效地改善合成孔径雷达(SAR)图像信息提取的效果,而乘性斑点噪声影响下的隐状态的估计是其中的关键问题,目前该问题还没有得到有效地解决.借用信息论领域中的Turbo迭代译码原理,针对SAR图像信号,提出一种新的隐状态的Turbo迭代估计方法.该方法在两个不相关的子空间上分别采用不同的约束条件对隐状态进行轮流地估计,并将其后验概率作为一种外信息进行交换.实验结果证明该方法具有优良的估计结果,并且收敛速度较快.

Turbo Iterative Estimation of State Parameters in Wavelet-Domain Hidden Markov Models of SAR Image

Using wavelet-domain hidden Markov models (HMMs) can efficiently improve the pe rformance of SAR image information extraction,where the key problem is how to e s timate the hidden state under the influence of multiplicative speckle noise,whi c h is not solved effectually yet.Making use of the principle of turbo iterative d ecoding in information theory and aiming at SAR image,the paper proposed a new met hod of turbo iterative estimation for the hidden state,in which the hidden stat e is estimated alternatively with two different restriction conditions in two unc orrelated sub-spaces,and the posterior probability,as an kind of extrinsic in fo rmation,is exchanged between the two sub-spaces.The experimental results illus t rate that the method has a rather impressive performance and very fast convergen ce rate.