基于区域确定的分层马尔可夫模型及其MPM算法  

A Region-determined Hierarchical Markov Model and Its MPM Algorithm

作　　者：杨勇[1] 孙洪[1] 何楚[1] 

机构地区：[1]武汉大学电子信息学院,武汉430079

出　　处：《自动化学报》2007年第7期693-697,共5页Acta Automatica Sinica

基　　金：国家自然科学基金(60372057;40376051)资助~~

摘　　要：基于四叉树的分层马尔可夫随机场(Markov random field,MRF)模型在层间存在因果性,不需要像非因果马尔可夫随机场模型那样的迭代算法,但是传统的分层MRF模型常常导致分割结果具有块状现象和非连续边缘．本文提出一种新的基于区域确定的半树分层MRF算法,并推导出它的最大后验边缘概率(Maximizer of the posteriori marginal,MPM)算法．在流域算法过分割结果的基础上,该模型将层间的点概率转换为区域概率,采用区域概率实现各层图像分割．从SAR图像的监督分割实验结果来看,本文提出的模型较好地克服了基于像素分层模型和单分辨率MRF模型带米的块现象和非连续边界,因而具有更好的分割结果．The noniterative algorithm of discrete hierarchical Markov random field （MRF） model has much lower computing complexity and better result than its iterative counterpart of noncausal MRF model, since it has causality property between layers. However, traditional hierarchical MRF model always results in the block artifacts and discontinuous edges. In this paper, a new region-determined half tree hierarchical MRF model is proposed and its region-determined maximizer of the posteriori marginals （MPM） algorithm is inferred. Based on over-segmentation of the watershed algorithm, the proposed model converts pixel probabilities between layers into region probabilities and obtains the final segmentation. The experiments on supervised SAR image segmentation demonstrate that the proposed method performs better than the pixel-based hierarchical model as well as the Gibbs sampler with the single resolution model.

关 键 词：分层马尔可夫随机场 区域概率 监督分割 最大后验边缘概率 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]