Hyperspectral anomaly target intelligent detection method based on robust spectral covariance distance

Abstract

The invention discloses a hyperspectral anomaly target intelligent detection method based on a robust spectral covariance distance, and the method comprises the following steps: constructing a spatialdimension factor matrix according to high-order singular value decomposition, so as to fully extract the spatial dimension information of a hyperspectral image; classifying all pixels of the hyperspectral data into k categories by using a clustering algorithm, removing pixels with the number of pixels less than P in a clustering cluster, and calculating kernel space anomaly indexes of the remaining pixels according to each cluster, so that the first P pixels with the maximum superposition sum are finally selected as constituent atoms of a spectral dimension factor matrix; establishing a hyperspectral image anomaly intelligent detection model based on robust spectral covariance distance regularization, constructing a Lagrange equation, iteratively solving a certain variable step by step while fixing other variables, solving an anomaly detection model, and obtaining an abnormal target according to the obtained solution. The method can achieve the intelligent detection of the abnormal target in a hyperspectral remote sensing image, and effectively reduces the false alarm rate.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, in particular to an intelligent detection method for hyperspectral abnormal targets based on robust spectral covariance distance. Background technique [0002] Anomaly target detection in hyperspectral remote sensing is an important application direction of hyperspectral remote sensing. The purpose of hyperspectral anomaly detection is to determine the position and category of the target of interest. It is essentially a binary classification problem. High resolution makes it possible to identify different ground objects. The spectral differences of different substances make the target image in the hyperspectral image There is a difference between the pixel and the background pixel, and the hyperspectral target detection can be realized by using the pixel difference. Traditional target detection methods generally require prior spectral knowledge and data spectral correctio...

AI Technical Summary

Problems solved by technology

[0005] The current tensor decomposition algorithm basically assumes isotropy, and the construction method of the factor matrix on each mode is the same, such as orthogonal constraints and non-negative constraints. In practice, this construction method has limitations and cannot be truly represented. Real characteristics in each dimension, high-dimensional tensor data show different characteristic information in different dimensions

Images