Abstract
Anomaly detection has been an important topic in hyperspectral image analysis. This technique is sometimes more preferable than the supervised target detection because it requires no a priori information for the interested materials. Many efforts have been made in this topic; however, they usually suffer from excessive time cost and a high false-positive rate. There are two major problems that lead to such a predicament. First, the construction of the background model and affinity estimation are often overcomplicated. Second, most of these methods have to impose a stringent assumption on the spectrum distribution of background; however, these assumptions cannot hold for all practical situations. Based on this consideration, this paper proposes a novel method allowing for fast yet accurate pixel-level hyperspectral anomaly detection. We claim the following main contributions: construct a high-order 2-D crossing approach to find the regions of rapid change in the spectrum, which runs without any a priori assumption; and design a low-complexity discrimination framework for fast hyperspectral anomaly detection, which can be implemented by a series of filtering operators with linear time cost. Experiments on three different hyperspectral images containing several pixel-level anomalies demonstrate the superiority of the proposed detector compared with the benchmark methods.
I. INTRODUCTION
HYPERSPECTRAL imaging systems have the ability to collect digital images with very densely sampled or nearly continuous radiance spectra for each pixel in the scene. The captured rich information about the spectral signatures can help identify minor differences between various materials. This characteristic enables hyperspectral images to be beneficial to a wide range of applications. For example, they have already been successfully applied to environmental monitoring [1], production quality inspection [2], medical imaging [3], biological analysis [4], etc.
V. CONCLUSION
Anomalies in the hyperspectral image often represent crucial occurrences worthy of further investigation. Therefore, reliably detecting these anomalies is important in both academia and industry. In this regard, traditional hyperspectral anomaly detectors are far from satisfying due to their excessive time costs and high FPRs. In this paper, a novel hyperspectral anomaly detector has been proposed based on the formulation of the high-order 2-D crossing analysis. The proposed detector is termed 2DCAD, which can allow for fast examination of the testing pixels with respect to their neighborhoods, without losing accuracy.