通过特征提取和背景净化相结合进行高光谱异常检测

摘要：异常检测（（ AD）因其在无需先验知识的情况下检测潜在目标的优势而成为高光谱图像（（ HSI）处理中的研究热点， 并且为了提高性能，各种算法都被提出。然而，它们通常要么无法提取HSI背后的内在特征，要么受到噪声和异常的污 染。针对这些问题，我们提出了一种新的异常检测器，它结合了分数阶傅里叶变换（（FrFT）和低秩稀疏矩阵分解（（LRaSMD）。 首先，通过FrFT提取HSI数据的显著特征。然后，采用比传统LRaSMD更实用、更稳定的行约束LRaSMD（（RC-LRaSMD） 将背景与噪声和异常分离。最后，我们实施了一种原子选择策略来构建用于检测的背景协方差矩阵。与其他最先进的检 测器相比，对多个HSI数据集的实验结果表明，该检测器具有令人满意的检测性能。

关键词：特征提取、高光谱异常检测、低秩稀疏矩阵分解、行稀疏性。

期刊：Geoscience and Remote Sensing Letters- IEEE

设备：GaiaField

Hyperspectral Anomaly Detection via Integration of Feature Extraction and Background Purification

Abstract：Anomaly detection (AD) has become a hotspot in hyperspectral imagery (HSI) processing due to its advantage in detecting potential targets without prior knowledge, and a variety of algorithms are proposed for a better performance. However, they usually either fail to extract intrinsic features underlying HSIs, or suffer from the contamination of noise and anomalies. To address these problems, we propose a new anomaly detector by integrating fractional Fourier transform (FrFT) with low rank and sparse matrix decomposition (LRaSMD). First, distinctive features of HSI data are extracted via FrFT. Then, row-constrained LRaSMD (RC-LRaSMD), which is more practical and stable than the traditional LRaSMD, is employed to separate background from noise and anomalies. Finally, we implement an atom-selection strategy to construct the background covariance matrix for detection. The experimental results with several HSI data sets demonstrate satisfying detection performance compared with other state-of-the-art detectors.

Keywords：Feature extraction, hyperspectral anomaly detection (AD), low rank and sparse matrix decomposition (LRaSMD), row-sparsity.