Image mosaic method, device, computer equipment and storage medium

Abstract

The embodiment of the present invention discloses an image mosaic method, device, computer equipment and storage medium. The method includes: based on the preliminary registration accuracy, acquiring the reference feature points of the reference image, and the search features of the search image corresponding to the reference feature points point; based on the preset registration accuracy, within the neighborhood of the search feature point, determine the position of the interpolation point with the greatest similarity to the reference feature point to update the search feature point, wherein the preset registration accuracy is higher than the preliminary registration Accuracy; according to the correspondence between the reference feature points and the updated search feature points, the reference image and the feature image are registered to generate a registration image; the stitching in the registration image is eliminated by image fusion to generate a stitching image. It solves the problem that the prior art cannot give consideration to both the image splicing effect and the splicing speed, and achieves the technical effect of not only ensuring the image splicing effect, but also improving the image splicing speed.

Description

technical field

[0001] Embodiments of the present invention relate to the field of image processing, and in particular, to an image splicing method, device, computer equipment, and storage medium. Background technique

[0002] Image stitching refers to the process of splicing two or more overlapping images describing the same scene into a new image of a large scene through image registration and image fusion technology. With the increasing demand for image analysis, more and more fields need to obtain panoramic images through image stitching, such as medicine, remote sensing technology and virtual reality and other fields.

[0003] The image stitching accuracy of the prior art includes pixel level and sub-pixel level. The former has a small amount of calculation and faster image stitching, but the registration accuracy of the stitched image is lower; although the registration accuracy of the latter stitched image is higher, However, the amount of calculation is large and th...

Images