摘要
介绍2种典型的统计匹配滤波器算法:自适应一致性估计(ACE)与约束能量最小化(CEM)。实验选取3种不同的背景区域(全景、除去目标的全景及部分均质场景)并计算其协方差,利用受试者工作特性(ROC)曲线中给定虚警概率下的检出概率(DR@FAR)和平均检出概率(ADR)指标,比较分析了背景区域变化对ACE与CEM算法目标探测性能的影响。
Statistical matched filter detection algorithms can be applied to target detection in hyperspectral imagery.The calculation of the background covariance matrix is used in any statistical matched filters,including Adaptive Coherence Estimator（ACE） and Constrained Energy Minimization（CEM） presented in this paper.Experiments on the calculation of the background covariance matrix from different background regions and the utilization of ROC curve give a comparative analysis of the problem as to how different background regions affect the detection performance of ACE and CEM.
出处
《国土资源遥感》
CSCD
2010年第2期26-29,共4页
Remote Sensing for Land & Resources
关键词
高光谱图像
目标探测
ROC曲线
性能指标
背景协方差矩阵
Hyperspectral imagery
Target detection
ROC curve
Performance metrics
Background covariance matrix
