摘要
针对高光谱图像复杂背景导致异常检测效果下降的问题,提出了一种新的异常检测方法。首先使用小波分解将原始高光谱图像分解成高频信息图像和低频信息图像,使用主成分分析(PCA)方法抑制高光谱原始图像的背景信息;然后将背景抑制后图像和高频信息图像融合,得到处理后图像;最后使用Kerner-Reed-Xiaoli(KRX)算法进行异常检测,并仿真证明了本文方法在提高异常检测效果和效率方面的有效性。
In order to overcome the bad influence caused by complex background in hyperspectral image a- nomaly detection,a new anomaly detection approach is proposed. Hyperspectral data is forstly decom- posed into high frequency images and low frequency image by wavelet decomposition, and the background information in hyperspectral date is also processed by principal component analysis (PCA). Then data af- ter processing is gotten by fusing high frequency images and data after PCA. At lastly, Kerner-Reed-Xiaoli (KRX) algorithm is used to detect the data after processing. The simulation results show that the ap- proach is better than other algorithms by comparing the receiver operating characteristic (ROC) curves.
出处
《光电子.激光》
EI
CAS
CSCD
北大核心
2016年第2期177-181,共5页
Journal of Optoelectronics·Laser
基金
吉林省科技发展计划资助项目(20140101213JC)资助项目
关键词
高光谱异常检测
小波分解
主成分分析(PCA)
KRX算法
hyperspectral image anomaly detection
wavelet decomposition
principal components analy-sis (PCA)
Kerner-Reed-Xiaoli (KRX) algorithm