Unmanned aerial vehicle image filtering frequency division jointing method

Abstract

The invention belongs to the field of unmanned aerial vehicle remote-sensing image processing, relates to an unmanned aerial vehicle image filtering frequency division jointing method and is mainly to solve the problems that the phenomenon of ghost and joint crack appears easily in the unmanned aerial vehicle image jointing process. The method is characterized by, to begin with, decomposing a unmanned aerial vehicle image pair to be jointed into a low-frequency image pair and a high-frequency image pair through Gaussian low-pass filtering; then, carrying out jointing processing on the low-frequency image pair through a weighted smooth fusion method, and searching an optimal jointing line through an improved dynamic programming algorithm to finish high-frequency image jointing; and finally, carrying out linear synthesis on the jointed low-frequency image pair and the high-frequency image pair to obtain a final joint image. The method can solve the problem of ghost phenomenon in the unmanned aerial vehicle image jointing process and prevent the appearance of the joint crack to the largest degree, and can achieve a good jointing effect for the unmanned aerial vehicle images, which are obvious in luminance difference.

Description

technical field [0001] The invention belongs to the field of UAV remote sensing image processing, in particular to a UAV image filter frequency division splicing method. Background technique [0002] The UAV remote sensing system has the characteristics of flexibility, real-time, and low cost. It has significant advantages in quickly acquiring high-resolution images in small areas and areas where flight is difficult. It has become a powerful means to improve the current situation of surveying and mapping results, and is widely used in military , In the field of civil surveying and mapping. However, limited by the flight height and camera angle of view, it is difficult for a single UAV image to completely cover the area of ​​interest, which greatly limits its application. In order to expand the field of view and obtain more information about the target area, it is necessary to stitch multiple UAV images with a certain degree of overlap. [0003] Due to the light weight of t...

AI Technical Summary

Problems solved by technology

Although this method can ensure that the texture structure of the overlapping area is consistent and avoid ghosting, it cannot guarantee that stitching seams can be avoided while overcoming ghosting.

Especially when there are obvious differences in brightness between adjacent images, even if the optimal stitching line is found, the stitching seam cannot be completely eliminated, and the natural transition of the overlapping area cannot be achieved.

[0006] Through the analysis of the two types of methods, when the images to be stitched have rich texture structures, or there are registration errors and large differences in radiance, satisfactory results cannot be achieved by relying on a single stitching method.

Images