Fisheye image correcting method for image stitching

Abstract

The invention provides a fisheye image correcting method for image stitching. The method corrects two fisheye images partially overlapped with each other through a computer, and finds out a splicing angle of stitching caused by pitch angles during shooting between the two fisheye images by adopting an unique correction principle and utilizing matched pixels in the two fisheye images so as to obtain the pitching angle formed during the shooting of the two fisheye images through backstepping; and the method also avoids adverse impacts, such as inclination, ghosting, and the like, of errors of the pitch angles formed during the shooting on the panorama stitching of the fisheye images through pitching conversion mapping treatment, and has the advantages of better robustness and high accuracy in computation.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a fisheye image correction method for image splicing. Background technique [0002] In many image processing fields such as panoramic display, landform acquisition, virtual reality, etc., it is usually required that the angle of view of a single photo is as wide as possible, so as to use less image resources and shorter time to complete image data collection and processing. Fisheye images, that is, images taken with fisheye lenses, have a wide field of view. Depending on the fisheye lens, the maximum viewing angle of fisheye images can reach 180° or even 220°, so it has been widely used in many fields. Especially in the field of panoramic image acquisition. [0003] In the field of panoramic image acquisition, taking advantage of the large angle of view and wide field of view of fisheye images, panoramic images can be obtained by shooting a few fisheye images. Tak...

AI Technical Summary

Problems solved by technology

[0004] The current distortion correction processing is usually carried out for a single fisheye image, and the pitch angle problem when the fisheye image is taken is not considered in the processing

However, in the actual shooting environment, due to many objective factors such as artificial shaking, poor ground flatness at the shooting point, tilted ground at the shooting point, and slight shaking of the lens rotation during shooting, it is very easy to cause pitch angles when shooting fisheye images. , the existence of the pitch angle leads to the perspective plane image after the fisheye image is directly processed by distortion correction, the original vertical lines still cannot be completely restored to vertical and there is a small angle of inclination, and the two adjacent fisheye images processed In the perspective plane image, the inclination direction of the small angle of the image overlap area is opposite, so that when the two perspective plane images are stitched together, the overlap area of ​​the image cannot be completely overlapped and ghosting occurs, which seriously affects the stitching quality of the panoramic image

Images