Recently, many collaborative representation (CR)-based algorithms have been proposed for hyperspectral anomaly detection (AD). CR-based detectors approximate the image by a linear combination of background dictionaries and the coefficient matrix and derive the detection map by utilizing recovery residuals. However, these CR-based detectors are often established on the premise of precise background features and strong image representation, which are very difficult to obtain. In addition, pursuing the coefficient matrix reinforced by the general l2l_{2} -min is very time-consuming. To address these issues, a nonnegative-constrained joint collaborative representation (NJCR) model is proposed in this article for the hyperspectral AD task. To extract reliable samples, a union dictionary consisting of background and anomaly subdictionaries is designed, where the background subdictionary is obtained at the superpixel level and the anomaly subdictionary is extracted by the predetection process. And the coefficient matrix is jointly optimized by the Frobenius norm regularization with a nonnegative constraint and a sum-to-one constraint. After the optimization process, the abnormal information is finally derived by calculating the residuals that exclude the assumed background information. To conduct comparable experiments, the proposed nonnegative-constrained joint collaborative representation (NJCR) model and its kernel version (KNJCR) are tested in four hyperspectral images (HSIs) datasets and achieve superior results compared with other state-of-the-art detectors. The codes of the proposed method will be available online (https://github.com/ShizhenChang/NJCR).

中文翻译：

---

用于高光谱异常检测的联合字典非负约束联合协作表示


最近，人们提出了许多基于协作表示（CR）的算法用于高光谱异常检测（AD）。基于 CR 的检测器通过背景字典和系数矩阵的线性组合来近似图像，并利用恢复残差导出检测图。然而，这些基于CR的检测器往往是建立在精确的背景特征和强大的图像表示的前提下的，而这是很难获得的。另外，求出一般的l2l_{2} -min强化的系数矩阵是非常耗时的。为了解决这些问题，本文提出了一种用于高光谱 AD 任务的非负约束联合协作表示（NJCR）模型。为了提取可靠样本，设计了由背景子词典和异常子词典组成的联合词典，其中背景子词典是在超像素级别获得的，异常子词典是通过预检测过程提取的。系数矩阵通过带有非负约束和和对一约束的Frobenius范数正则化联合优化。经过优化过程后，通过计算排除假设背景信息的残差，最终得出异常信息。为了进行可比较的实验，所提出的非负约束联合协作表示（NJCR）模型及其内核版本（KNJCR）在四个高光谱图像（HSI）数据集中进行了测试，并与其他最先进的检测器相比取得了优异的结果。该方法的代码将在线提供（https://github.com/ShizhenChang/NJCR）。