Hyperspectral remote sensing image target detecting method based on variable end members

Abstract

The invention discloses a hyperspectral remote sensing image target detecting method based on variable end members, comprising the following steps of: selecting a remote sensing image to be processed by target detection; acquiring prior information required for detection, wherein the prior information comprises spectral information of target end members and spectral information of background end members; traversing the remote sensing image to be detected by utilizing a cross correlation matching technique to determine the types of background end members in each pixel in the remote sensing image to be detected; carrying out spectral decomposition on the remote sensing image to be detected in a completely restricted least square way to acquire the component information of target end members and various background end members in each pixel in the remote sensing image to be detected; establishing a detector based on the GLRT (Generalized Likelihood Ratio Test); and traversing the remote sensing image to be detected by adopting the detector to acquire the detection function value of each pixel in the remote sensing image to be detected, thereby judging whether targets exist in each pixel in the remote sensing image to be detected or not. The method of the invention has the characteristics of strong structuration, high adaptability, self-organization and self-learning.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, in particular to a hyperspectral remote sensing image target detection method. Background technique [0002] In hyperspectral remote sensing images, the distribution of ground objects is relatively complex, and the extraction of objects of interest such as artificial buildings and moving vehicles is a difficult problem. Due to the limitation of spatial resolution, the phenomenon of mixed pixels is common in hyperspectral remote sensing images. The phenomenon of mixed pixels means that the pixels on the image are not composed of reflection signals corresponding to a single type of ground object, but formed by the combined action of different signals of multiple types of ground objects. Therefore, the spectrum reflected by the mixed pixel on the hyperspectral remote sensing image is a mixture of multiple spectra. In this case, target detection methods based on spectral fea...

AI Technical Summary

Problems solved by technology

In practice, the number and types of endmembers contained in each pixel are usually different, so it is not accurate to use all endmembers to construct the detector, so it may eventually lead to a decrease in the separability of the target and the background

Images