Multi-temporal/multi-modal remote sensing image registration method based on gaussian-hermite moments

Abstract

The invention relates to a multi-temporal / multi-mode remote sensing image registration method based on Gaussian-Hermite moments. The Gaussian-Hermite moments are an image feature describing method proposed by shen in 1997. The method is mainly applied to the image fields of classification, target detection, image reconstruction and the like at present, and good results are obtained. In 2010, Bo Yang and others construct eighteen fifth-order Gaussian-Hermite moments based on the original Gaussian-Hermite moments and prove that the group of Gaussian-Hermite moments has rotation and translation invariances. Therefore, on the basis of researching the Gaussian-Hermite moments, Gaussian-Hermite moments feature descriptors are constructed for corner feature points of images by the aid of the rotation and translation invariances of the Gaussian-Hermite moments, coarse registration of the images is realized by means of measurement of similarities between feature vectors, and mismatched point pairs are eliminated by an RANSCA (random sample consensus) algorithm so as to achieve accurate registration of the images.

Description

technical field [0001] The invention belongs to a Gaussian-Hermite moment-based multitemporal / multimodal remote sensing image registration method, in particular to a Gaussian-Hermite moment-based multitemporal / multimodal remote sensing image registration method. Background technique [0002] With the rapid development of modern science and technology, especially the development of aviation / aerospace technology, imaging technology, data communication technology and the continuous updating of new sensors, remote sensing technology has entered a state that can dynamically, quickly and accurately provide a variety of target observation data. The new stage of remote sensing data has made people's ability to obtain remote sensing data continuously improved, and the amount of data information obtained has become more and more abundant, and the types have become more and more diverse, such as hyperspectral images, multispectral images, and multitemporal images. The remote sensing im...

AI Technical Summary

Problems solved by technology

[0005] In order to avoid the deficiencies of the prior art, the present invention proposes a Gaussian-Hermite moment-based multi-temporal / multi-modal remote sensing image registration method, which overcomes the problem that the prior art method is not easy to achieve grayscale or contrast. Remote sensing image registration, and the shortcomings of relatively low image registration accuracy

Images