一种改进的高光谱图像中多小目标检测算法  

A Revised Multi-Target Detection Approach in Hyperspectral Image

作　　者：尹继豪[1] 王艳[1] 王义松[1] 

机构地区：[1]北京航空航天大学,北京100191

出　　处：《电子学报》2010年第9期1975-1978,共4页Acta Electronica Sinica

基　　金：航天科技创新基金(No.CASC200904);CAST创新基金(No.CAST200811);武器装备预研基金

摘　　要：针对高光谱图像小目标检测中约束能量最小化算法对噪音敏感且不能区分相似目标的问题,基于多目标约束能量最小化、加和约束能量最小化、胜者全赢约束能量最小化算法,提出一种改进的多个小目标检测算法.该算法对原有算法中自相关矩阵进行修正,减少了目标向量对自相关矩阵的影响.仿真实验表明,改进后的多小目标检测算法,检测误差明显低于原有算法.Constrained energy minimization（CEM） algorithm is very sensitive to noise and cannot classify the same type of targets with similar signatures,so we propose a revised multi-target detection approach,which is based on multiple-target constrained energy minimization（MTCEM）,sum constrained energy minimization（SCEM） and winner-take-All constrained energy minimization（WTACEM）.This approach revised autocorrelation matrix in original approach by excluding the desired target pixel vectors from the autocorrelation matrix.The simulation results indicate that the errors caused by the revised multi-target detection approach have decreased obviously.

关 键 词：多目标检测 自相关矩阵 约束能量最小化 高光谱图像 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]