联合低秩张量分解与稀疏表示的高光谱异常目标检测算法  

Joint Low-Rank Tensor Decomposition and Sparse Representation of Anomaly Target Detection for Hyperspectral Imagery

作　　者：成宝芝 张丽丽 赵春晖[3] CHENG Baozhi;ZHANG Lili;ZHAO Chunhui(School of Computer Information and Engineering Changzhou Institute of Technology,Changzhou 213000 China;College of Mechanical and Electrical Engineering Daqing Normal University,Daqing 163000 China;College of Information and Communication Harbin Engineering University,Harbin 150000 China)

机构地区：[1]常州工学院计算机信息工程学院,江苏常州213000 [2]大庆师范学院机电工程学院,黑龙江大庆163000 [3]哈尔滨工程大学信息与通信工程学院,哈尔滨150000

出　　处：《电光与控制》2023年第1期57-62,共6页Electronics Optics & Control

基　　金：黑龙江省自然科学基金(LH2019F040);大庆师范学院科学研究基金(19ZR02)。

摘　　要：异常目标检测是当前高光谱图像处理中的一个研究热点。针对当前异常目标检测算法存在的问题,从解决高光谱图像中含有的背景、异常目标和噪声等相关量出发,利用高光谱图像的空间谱和光谱特性,提出了联合低秩张量分解和稀疏表示的新的高光谱图像异常目标检测算法。该算法首先利用低秩张量分解模型对高光谱进行图像恢复,使图像质量得到提升,从而使得异常目标变得突出,易于进行目标检测;然后,再利用稀疏差异指数进行异常目标检测,得到需要的异常检测结果;最后,利用真实的高光谱图像进行仿真实验,结果表明,新的异常目标检测算法具有检测精度高、虚警率低和鲁棒性好的特点。Anomaly target detection is a research hotspot in hyperspectral imagery processing.Aiming at the problems of current anomaly target detection algorithms,a new anomaly target detection algorithm is proposed by combining low-rank tensor decomposition with sparse representation for hyperspectral imagery.The algorithm utilizes the spatial spectrum and spectral characteristics by solving the problems of background,anomaly target and noise in hyperspectral imagery.Firstly,the algorithm uses the low-rank tensor decomposition to restore the original hyperspectral imagery,so that the image quality is improved,and the anomaly target becomes prominent and easy to be detected.Then,the sparse difference index is used for anomaly target detection to obtain the required anomaly detection results.Finally,simulation experiments are carried out by using real hyperspectral images.The results show that the new anomaly target detection algorithm has the characteristics of high detection accuracy,low false alarm rate and good robustness.

关 键 词：高光谱图像 异常目标检测 张量分解 稀疏表示 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]