Fisheye image distortion correction method based on elliptical division

Abstract

The invention discloses a fisheye image distortion correction method based on elliptical division, and belongs to the technical field of machine vision. The method mainly comprises the steps of calculating center coordinates and radius of a fisheye image, converting the fisheye image into a standard circle mode, dividing the fisheye image into four parts with two diagonal lines, and fitting each part with one part of an elliptic curve. According to the fisheye image distortion correction method based on the elliptical division, a coordinate mapping table is adopted to record a coordinate mapping relation between the fisheye image and a corrected image in the correction process, thus the coordinate mapping relation needs to be calculated only once, the algorithm effect and timeliness are good, and the method is applicable to real-time correction display of the fisheye image.

Description

technical field [0001] The invention belongs to the technical field of machine vision, and in particular relates to a fisheye image distortion correction method based on ellipse segmentation. Background technique [0002] The fisheye lens is a super wide-angle lens with a field of view of 170°-185°. In order to achieve the maximum viewing angle of the lens, the front lens of the lens has a short diameter and protrudes toward the front of the lens in a parabolic shape. The fisheye lens has a short focal length and a large viewing angle, and there is a geometric optical error between the imaging point and the ideal imaging point, also known as distortion. The distortion of the fisheye lens mainly includes radial distortion and tangential distortion. The radial distortion of the fisheye lens The main feature is that there is no distortion in the center, and the farther away from the center, the more serious the distortion. The tangential distortion of a fisheye lens is caused ...

AI Technical Summary

Problems solved by technology

[0007] In summary, although the correction method based on the projection model has a good effect, it cannot completely correct the fisheye image on one image; according to the correction algorithm based on the plane (2D), although it can completely correct the fisheye image on one image However, the pixels in both dimensions of the fisheye image cannot be corrected well at the same time, and the distortion of the edge is still very serious; the correction algorithm based on the stereoscopic image (3D) is more representative of the calibration correction method, which requires The camera parameters and distortion parameters are obtained in advance, and the correction effect is good, but there is a loss of image information

Images