Hyperspectral image anomaly detection method using multi-window feature analysis

Abstract

The invention provides a hyperspectral image anomaly detection method using multi-window feature analysis. The hyperspectral image anomaly detection method comprises the following steps: at first, determining the size of detected windows including an inner-layer window, a middle-layer window and an outer-layer window; next, calculating an OSP (Orthogonal Subspace Projection) operator in the outer-layer window, eliminating background interferences in the inner-layer window and the middle-layer window, and effectively removing white noise; then, carrying out background image element selection in the middle-layer window; and then, calculating a KRX (Kernel RX) operator in the inner-layer window, and carrying out anomaly detection on an image element to be detected; finally, outputting a detection result. According to the hyperspectral image anomaly detection method, a detection mode for three layers of windows is skillfully applied, and hyperspectral data is subjected to noise interference elimination at first and then is subjected to anomaly detection by using two layers of local background pixel windows. The interferences or the white noises emitted by uninterested signal sources in the inner-layer window and the middle-layer window are eliminated by using the OSP operator in the outer-layer window, so that the false alarm probability is reduced and better detection effect is obtained. A simulation experiment is carried out by using AVIRIS (Airborne Visible / Infrared Imaging Spectrometer) hyperspectral data, the detection performance of the hyperspectral image anomaly detection method provided by the invention is remarkably superior to the traditional algorithm, the false alarm possibility is reduced, and better detection effect is gained.

Description

technical field [0001] The invention relates to a hyperspectral anomaly detection method. Specifically, a hyperspectral anomaly detection method using multi-window feature analysis. Background technique [0002] As an important application of hyperspectral data, target detection has attracted extensive attention of researchers. It refers to the search for sparse pixels of known or unknown target spectral shape in a hyperspectral image cube. According to the detection theory, hyperspectral image target detection technology is mainly divided into two categories: target detection technology with known target spectral characteristics and anomaly detection technology with unknown target spectral characteristics. Traditional target detection technology is based on certain prior information (such as spectral database and real measurement results), but in practical applications, it is very difficult to obtain this prior information, which is mainly reflected in the The following ...

AI Technical Summary

Problems solved by technology

[0004] However, the traditional algorithm uses a local double-window detection model in the detection process. In this double-window detection model, the influence of noise on detection is often ignored, and the detection operator is directly used to detect the abnormality of the target pixel, so that Detection is greatly affected by noise, and good detection results cannot be achieved

Images