A method and system for generating hyperspectral images with large field of view of unmanned aerial vehicle

Abstract

The invention discloses a method and system for generating a hyperspectral image with a large field of view of an unmanned aerial vehicle. The method of the invention includes inputting a reference hyperspectral image collected by an unmanned aerial vehicle and a hyperspectral image to be spliced, and converting the hyperspectral image to be spliced ​​one by one. Transform the bands to the same coordinate system of the reference hyperspectral image, determine the overlapping area of ​​the reference hyperspectral image and the hyperspectral image to be stitched; use the overlapping area to perform spectral consistency correction for each band of the hyperspectral image to be stitched; calculate the reference hyperspectral image , The best stitching line of the overlapping region of the hyperspectral image to be stitched, using the weighted pyramid image fusion strategy, based on the best stitching line to fuse the hyperspectral image band by band, to obtain the final seamless stitching large field of view hyperspectral image. The present invention can accurately complete seamless splicing in an actual scene where the overlapping ratio of adjacent hyperspectral strip images is low, generate a hyperspectral image with a large field of view, and effectively eliminate the problem of spectral inconsistency.

Description

technical field [0001] The invention relates to image processing technology, in particular to a method and system for generating hyperspectral images with a large field of view of an unmanned aerial vehicle. Background technique [0002] Hyperspectral imagery is a special multi-band image, and each ground object has its unique spectral curve in hyperspectral imagery. Taking advantage of this feature, hyperspectral imagery has been successfully applied to mineral mapping and crop index estimation, etc. Various applications. In most cases, hyperspectral images are acquired by hyperspectral imager satellites. However, remote sensing satellites are photographed above clouds, so most channels in satellite hyperspectral images are susceptible to cloud interference, and such interference is difficult to eliminate. In addition, the inherent characteristics of low spatial resolution and long revisit period make it difficult for remote sensing satellites to obtain high-quality, mult...

AI Technical Summary

Problems solved by technology

Direct stitching of source images will lead to inconsistencies in the spectra of stitching results, which will adversely affect subsequent applications

In addition, in order to improve efficiency, when UAVs collect hyperspectral data, the overlap rate is usually set below 50%, which increases the difficulty of stitching algorithms based on image registration.

Images