摘要
提出一种改进的自适应余弦估计(ACE)目标检测算法。比较高光谱影像每个样本像元与目标信号的光谱相似度,选择与目标信号光谱差异性较大部分样本像元参与背景协方差阵的构建,可使背景协方差阵有效避免目标信息的"污染"。对航空可见光/红外成像光谱仪(AVIRIS)获取的两幅真实高光谱遥感影像进行了实验,结果表明,与另外两种ACE算法相比,改进算法的检测性能有明显改善,适合检测一定像元数目的大目标。
An improved adaptive cosine estimator（ACE）target detection algorithm was developed,in which the spectral similarity between each sample pixel and the target signal was compared.Based on the comparison,samples with greater spectral difference from the target signal were selected to take part in the building of background covariance matrix,which reduced the matrix＇s＂pollution＂of target information.Two real AVIRIS hyperspectral remote sensing images were tested for target detection.The experimental results demonstrate that compared with the other two ACE algorithms,the proposed algorithm yields better detection performance and is more suitable for detecting bigger targets occupying a number of pixels.
出处
《山东科技大学学报（自然科学版）》
CAS
2015年第3期62-67,共6页
Journal of Shandong University of Science and Technology(Natural Science)
基金
国家自然科学基金项目(41174093)
关键词
高光谱遥感
目标检测
自适应余弦估计
hyperspectral remote sensing
target detection
adaptive cosine estimator
