整体视觉统计模型在地物识别中的算法研究  

Overall Visual Statistical Model for Object Recognition on Remote Sensing Image

作　　者：刘玮[1] 田金文[1] 

机构地区：[1]华中科技大学图像识别与人工智能研究所多谱信息处理技术国防重点实验室,武汉430074

出　　处：《光电工程》2009年第3期102-109,共8页Opto-Electronic Engineering

基　　金：863项目资助(2007AA12Z153)

摘　　要：本文在结构化模型方法的基础上提出了目标的整体视觉统计模型,整体视觉模型不但考虑了目标的局部特征,而且还考虑的目标局部之间的空间位置关系。对局部特征和位置特征分别建模,局部特征根据应用选择,位置特征以树状图模型来表示,并且模型采用了统计的方法来表述结构化图模型,将能量最小问题转化为统计中的MAP问题,简化了问题的求解。本文将这一模型应用于遥感图像的典型地物识别之中,不但能够识别单目标还可以识别多目标,识别率较高,且定位较准确。The overaU visual statistical model is put forward based on the structural model. This model not only considers the local features of the objects but also considers the spacial information between objects. The model of local parts which are chosen depending on application, and the model of connection between parts are built separately which are expressed by graph model. We simplify the problem by minimizing the energy function into MAP problem based on the statistical model. In this paper, this model is applied to the typical object recognition of remote sensing image and this model works well not only on single target detection but also on multiple target localization.

关 键 词：整体视觉模型 统计模型 目标识别 目标定位 遥感图像 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]