Hyperspectral Remote Sensing Image Anomaly Detection Method Based on Low-rank Joint Collaborative Representation

Abstract

The invention discloses a hyperspectral remote sensing image anomaly detection method based on low-rank joint cooperative representation. A hyperspectral remote sensing image is divided into two parts: background and abnormal target. The background part is linearly represented by a dictionary, wherein the dictionary atoms are set by setting Two threshold parameters are effectively selected, and the coefficient matrix adopts low rank and l 2 Norm is constrained; anomaly targets are sparsely constrained. The invention can solve the problem of abnormal pixel pollution in the representation-based method, and effectively improves the accuracy of hyperspectral abnormal detection by using the synergy between dictionary atoms.

Description

Anomaly detection method in hyperspectral remote sensing images based on low-rank joint collaborative representation technical field The invention belongs to the technical field of hyperspectral remote sensing image processing, and is specifically related to a high Anomaly detection method in spectral remote sensing images. Background technique Hyperspectral remote sensing is a multi-dimensional information acquisition technology that combines imaging technology with spectral technology. Two-dimensional geometric spatial information and one-dimensional spectral information of the target, and obtain hundreds of continuous, narrow-band images with high spectral resolution image data with a spectral resolution of 10 -2 ~10 -1 λ. Different from traditional multispectral remote sensing, the main features of hyperspectral remote sensing It is: high spectral resolution, multiple and continuous bands, large amount of data and unified map. The band range of hyperspe...

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a hyperspectral remote sensing image anomaly detection method that can effectively solve the problem of hyperspectral remote sensing image anomaly detection dictionary construction and abnormal pixel pollution under the representation model, which is a low-rank joint cooperative representation

Images