基于图正则化低秩协同表示的高光谱异常检测

Graph Regularized Low-Rank and Collaborative Representation for Hyperspectral Anomaly Detection

高光谱异常检测是检测出与周围背景像素的光谱具有明显差异的目标的过程。研究学者针对高光谱异常检测提出了多种算法,其中低秩协同表示检测器(LRCRD)不仅能够考虑所有像素之间的高光谱相关性,而且用低秩和l范数最小化约束字典的系数矩阵,背景字典不需要过度完备,可以更好地表示背景。然而,LRCRD模型并没有考虑到高光谱数据的局部几何信息对于区分背景和异常像素的重要性。将图拉普拉斯正则项引入LRCRD模型中,提出了一种基于图正则化低秩协同表示的异常检测方法,分析数据中的非线性几何信息。该方法保持高光谱图像的局部几何结构,提高了检测精度。在合成和真实高光谱数据集上对所提方法进行了实验验证,实验结果证明了所提方法的可行性。

The aim of hyperspectral anomaly detection is to find targets that are spectrally distinct from their surrounding background pixels. Many algorithms for hyperspectral anomaly detection have been proposed by researchers. Among these, the low-rank and collaborative representation detector(LRCRD) can not only analyze the hyperspectral correlation between all pixels but also constrain the coefficient matrix of the dictionary using low-rank and lnorms minimization, which does not require an over-complete dictionary and is more useful for background modeling. However, the LRCRD model ignores the significance of the hyperspectral data’s local geometric information to distinguish between background and anomalous pixels. In this paper, the graph-Laplacian regularization is incorporated into the LRCRD formulation and a novel anomaly detection method is proposed based on the graph regularized LRCRD model to analyze nonlinear geometric information. The proposed preserves local geometrical structure in hyperspectral images, thereby improving detection accuracy. The experiments on synthetic and real hyperspectral datasets demonstrate the feasibility of the proposed method.