Aerial image splicing and positioning method based on aerial strip GPS and scale invariant constraints

Abstract

The invention discloses an aerial image splicing and positioning method based on an aerial strip GPS and scale invariant constraints, and belongs to the technical field of graphic image conversion andimage calibration. The method comprises the steps: preprocessing a to-be-spliced image; according to traditional feature point extraction and description, obtaining an accurate matching result through a BF matching method and an RANSAC method, calculating an affine transformation matrix for the feature matching result through scale invariant constraints, constructing second flight strip splicingthrough existing flight path information, and fusing a GPS into a panorama. According to the invention, the splicing quality of images between air strips is improved by using air strip GPS informationand scale invariant constraints, the problem of single air strip splicing deformation caused by the pitch angle is eliminated, the pixel center point coordinates of a subsequent splicing frame are restrained through the mapping relation obtained through the first air strip, the splicing effect of multiple air strips is improved, and the high GPS positioning precision is further achieved.

Description

technical field [0001] The invention belongs to the technical field of graphic image conversion and image calibration, in particular to an aerial image splicing and positioning method based on navigation belt GPS and scale-invariant constraints. Background technique [0002] An unmanned aerial vehicle (UAV) is an unmanned aircraft operated by radio remote control equipment and self-contained program control device, or operated completely or intermittently autonomously by an on-board computer. At present, it has a very wide range of applications in the fields of aerial photography, agriculture, plant protection, express transportation, disaster relief, surveying and mapping, power inspection, disaster relief and so on. [0003] At present, the most extensive demand for UAVs focuses on splicing and positioning, that is, to obtain image information in the flight area and the position information of the target in the picture by splicing aerial images. [0004] At present, the i...

AI Technical Summary

Problems solved by technology

[0005] For image stitching, the existing technology is suitable for the stitching of a single flight belt image, but when multiple flight belts are stitched together, two or more flight belt images often appear in dislocation; in addition, due to the pitch angle generated during the operation of the UAV, It will lead to splicing deformation of a single flight belt

For positioning, the existing technology will have errors when calculating the resolution and scale of each frame of image, and the overall error of the spliced ​​image will gradually accumulate as the splicing process continues, resulting in a serious drop in positioning accuracy

Images