Anomaly detection has become an important remote sensing application due to the abundant spectral and spatial information contained in hyperspectral images. Recently, hyperspectral anomaly detection methods based on the collaborative representation (CR) model have attracted significant attention. Nevertheless, these methods have to face two main challenges: 1) all features (spectral signatures) are constrained to share the same representation coefficient, which ignores the differences among features and 2) existing dictionaries for pixel-by-pixel detection models are usually not reliable. To address these issues, this article proposes a new relaxed CR detector for hyperspectral anomaly detection by using a novel nonglobal dictionary. The proposed detector conducts CR on each feature dimension of the pixel under test and simultaneously constrains the coding vectors of different features to be similar. To the best of our knowledge, this is the first time that a detection model is built from each feature dimension. To adjust the contributions of each feature, an adaptive feature weight constrained version of the method is also proposed. The nonglobal dictionary is constructed by combining the k{k} -nearest neighbor method and an existing global dictionary, which is more reliable and practical than the widely used dual-window dictionary. In addition, this article also designs a band selection strategy for the proposed method. Experiments on five real datasets indicate that the proposed method suppresses background well and outperforms other classical and state-of-the-art methods.

中文翻译：

---

具有轻松协作表示的高光谱异常检测


由于高光谱图像中包含丰富的光谱和空间信息，异常检测已成为重要的遥感应用。近年来，基于协作表示（CR）模型的高光谱异常检测方法引起了广泛关注。然而，这些方法必须面临两个主要挑战：1）所有特征（光谱特征）都被限制为共享相同的表示系数，这忽略了特征之间的差异；2）现有的逐像素检测模型字典通常不是可靠的。为了解决这些问题，本文提出了一种新的宽松 CR 检测器，通过使用新型非全局字典进行高光谱异常检测。所提出的检测器对被测像素的每个特征维度进行CR，同时约束不同特征的编码向量相似。据我们所知，这是第一次从每个特征维度构建检测模型。为了调整每个特征的贡献，还提出了该方法的自适应特征权重约束版本。非全局字典是通过k{k}最近邻法和现有的全局字典相结合构建的，比广泛使用的双窗口字典更加可靠和实用。此外，本文还为所提出的方法设计了频带选择策略。对五个真实数据集的实验表明，所提出的方法可以很好地抑制背景，并且优于其他经典和最先进的方法。