Low-rank expression and learning dictionary-based hyperspectral image abnormity detection algorithm

Abstract

The invention belongs to the technical field of remote sensing image processing, and specifically relates to a low-rank expression and learning dictionary-based hyperspectral image abnormity detection algorithm. According to the algorithm, a method for introducing low-rank expression in the abnormity detection problems is used for decomposing the two-dimensional hyperspectral image data into the sum of a low-rank matrix expressing background and a sparse matrix expressing abnormity, and then enabling a basic abnormity detection algorithm to act on the sparse matrix to obtain the abnormity detection result; and furthermore, the concept of a learning dictionary is imported in the low-rank expression algorithm, and the learning dictionary is obtained through an algorithm of random selection and gradient descent and is capable of expressing the background spectrums in hyperspectral images. Through the importing of the learning dictionary, the abnormity information can be better separated from the hyperspectral image data, so that better detection result can be obtained; and meanwhile, the robustness of the algorithm for the initial parameters can be improved, so that the computing cost is reduced and important value is provided for the actual abnormity detection application.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a hyperspectral anomaly detection algorithm. Background technique [0002] Remote sensing technology is a new comprehensive technology developed in the 1960s. It is closely related to science and technology such as space, electron optics, computer, and geography. It is one of the most powerful technical means for studying the earth's resources and environment. Hyperspectral remote sensing is a multi-dimensional information acquisition technology that combines imaging technology with spectral technology. Its image has the characteristics of high spectral resolution and map-spectrum integration. It has unique advantages in the field of object detection, and has important applications in environmental monitoring, military reconnaissance and other fields. In practical situations, it is often difficult for researchers to obtain the spectral charact...

AI Technical Summary

Problems solved by technology

However, the traditional anomaly detection algorithm based on statistical models has the following defects: 1) the background of the actual hyperspectral remote sensing image does not completely obey the Gaussian distribution; 2) the calculation process of the background covariance matrix is ​​often polluted by abnormal targets

[0008] Principal component analysis (PCA) completes data dimensionality reduction by finding a linear model of the subspace, which can effectively remove Gaussian noise in the data. However, when there are relatively large noises or abnormalities in the data, the effect of PCA is not ideal.

Images