Abstract
Hyperspectral anomaly detection methods are often limited by the effects of redundant information and isolated noise. Here, a novel hyperspectral anomaly detection method based on harmonic analysis (HA) and low rank decomposition is proposed. This paper introduces three main innovations: first and foremost, in order to extract low-order harmonic images, a single-pixel-related HA was introduced to reduce dimension and remove redundant information in the original hyperspectral image (HSI). Additionally, adopting the guided filtering (GF) and differential operation, a novel background dictionary construction method was proposed to acquire the initial smoothed images suppressing some isolated noise, while simultaneously constructing a discriminative background dictionary. Last but not least, the original HSI was replaced by the initial smoothed images for a low-rank decomposition via the background dictionary. This operation took advantage of the low-rank attribute of background and the sparse attribute of anomaly. We could finally get the anomaly objectives through the sparse matrix calculated from the low-rank decomposition. The experiments compared the detection performance of the proposed method and seven state-of-the-art methods in a synthetic HSI and two real-world HSIs. Besides qualitative assessment, we also plotted the receiver operating characteristic (ROC) curve of each method and report the respective area under the curve (AUC) for quantitative comparison. Compared with the alternative methods, the experimental results illustrated the superior performance and satisfactory results of the proposed method in terms of visual characteristics, ROC curves and AUC values.
Highlights
Hyperspectral image (HSI), which is an image cube that simultaneously acquires spatial information and rich spectral information of the objects, has high spectral resolution (10 nm or less) and a wide spectral coverage [1]
Detection is an unsupervised method, which is more practical than supervised target detection because it does not require the prior information of the target
The area under the curve (AUC) value is obtained by calculating the area under the receiver operating characteristic (ROC) curve of anomaly detector
Summary
Hyperspectral image (HSI), which is an image cube that simultaneously acquires spatial information and rich spectral information of the objects, has high spectral resolution (10 nm or less) and a wide spectral coverage (from visible to short-wave infrared) [1]. Target detection and recognition can be performed by the spatial-spectral information provided by the HSI [4,5]. According to whether priori information is used, the target detection methods are classified into two categories: supervised and unsupervised [6]. Detection is an unsupervised method, which is more practical than supervised target detection because it does not require the prior information of the target. Detection has been widely applied to the fields of maritime search and rescue, geological survey, fire disaster monitoring and battlefield target detection [7]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have