基于类对可分和灰色决策的高光谱波段选择方法  

Hyperspectral Band Selection Method Based on Conjugate Class Separability and Grey Decision

作　　者：张海涛[1] 王鹤桥[1] 孟祥羽[1] 武文波[1] 

机构地区：[1]辽宁工程技术大学软件学院,葫芦岛125105

出　　处：《计算机科学》2014年第6期309-313,共5页Computer Science

基　　金：国家自然科学基金(61172144)资助

摘　　要：随着研究者对高光谱图像光谱信息的质量要求逐渐提高,其自身特点给图像信息的进一步提取带来了阻碍。现有单一波段选择方法不能完全顾及"信息量、相关性、类别可分性"3点准则,所得结果不可避免地受其他指标度量所约束。而利用灰色系统理论以小样本、贫信息、不确定性系统作为研究对象的属性,可以在将高光谱数据划分为子空间的基础上,进行灰色关联决策运算,从而克服了单指标度量的独立性与不相容性。因此,针对"确保类对可分"这日益高涨的需求,提出一种通过引入灰色关联决策对单一波段选择结果进行综合考量的波段选择方法。最后,通过实验与常见融合方法进行了对比。As researchers＇ demand for the quality of the spectral information in hyperspectral images gradually increases,the characteristics of hyperspectral images impedes the further information extraction to the images.The existing single band selection method can not fully consider the criterias about ＂information content,correlativity,class separability＂,and the results are inevitably restricted by other index measurements.Using the quality of grey system theory and taking the small sample,small information and uncertainty system as research subjects can do the grey incidence decision on the basis of subspace partition,overcoming the independence and incompatibility of the single-index measure.Therefore,aiming at the growing demand about ensuring the separability of conjugate class,this paper put forward a band selection method which can synthetically consider the results of other single band selection mehtods with grey incidence decision.Finally,an experiment was made and it was compared with common fusion methods.

关 键 词：波段选择 子空间划分 BHATTACHARYYA距离 灰色关联决策 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]