遥感影像像斑综合相邻势能分析的随机场模型  

Random Field Model Based on Segments Spatial Integrated Adjacent Potential Energy Analysis for Remote Sensing Image

作　　者：龚龑[1] 李亮[1] 王琰[2] 陶醉[3] 

机构地区：[1]武汉大学遥感信息工程学院,武汉市430079 [2]中国科学院软件研究所,北京市100190 [3]中国科学院遥感与数字地球研究所,北京100190

出　　处：《武汉大学学报（信息科学版）》2013年第12期1470-1474,共5页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(41101412);国家863计划资助项目(2013AA102401);中央高校基本科研业务专项基金资助项目(3101009)

摘　　要：针对当前像斑随机场模型无法充分描述方位特征的不足,在RAG-MRF模型的基础上提出了一种基于综合相邻势能分析的随机场模型,采用了新型的基于统计的邻域势函数,并设计了相应的像斑空间相邻特征描述指标,以提升像斑分类及识别的效果。As compared to a pixels＇ regular neighborhood system, the morphology and distribution of segments are irregular, which makes the quantity of neighborhood cliques in RAG-MRF unpredictable, and therefore the quantification of segments＇ orientation features becomes impossible. Aimed at the disadvantages of current segments-based random field in orientation feature, we propose a random field model based on segments spatial integrated adjacent potential energy analysis, a new neighborhood potential energy function based on statistic was used, and according spatial adjacent feature indices for segments was designed, and the results of classify or recognition was improved.

关 键 词：像斑 方位特征 空间关系 随机场 空间邻接 

分 类 号：P237.4[天文地球—摄影测量与遥感] TP753[天文地球—测绘科学与技术]