Method for calibrating parabolic catadioptric camera by using tangential two-ball image and orthogonal vanishing points

Abstract

The present invention relates to a method for calibrating a parabolic catadioptric camera by using a tangential two-ball image and orthogonal vanishing points. The method comprises: firstly using a parabolic catadioptric camera to shoot two images of a target, wherein the target is two balls with tangential projections on an image plane; in each image, obtaining an antipodal image point according to a relationship between an image point and the antipodal image point of the image point, thereby estimating an antipodal ball image of the two-ball image in a catadioptric image, and solving real and virtual intersection points of the two-ball image and real and real and virtual intersection points of the antipodal ball image; secondly, determining three groups of orthogonal vanishing points according to three groups of antipodal image points correspondingly formed by the intersection points of the ball image and the intersection points of the antipodal ball image, wherein six groups of orthogonal vanishing points can be determined from the two images; and finally, solving an intrinsic parameter of the camera by using constraint of the orthogonal vanishing points on the intrinsic parameter of the camera. By using the method provided by the present invention, full-automatic calibration can be realized, so that errors caused by measurement in a calibration process are reduced. Because projection contour lines of the balls in the image can be completely extracted, so that calibration precision of the camera is improved.

Description

technical field [0001] The invention belongs to the field of computer vision and relates to a method for solving internal parameters of a parabolic catadioptric camera by using tangent double spheres and orthogonal vanishing points. Background technique [0002] The central task of computer vision is to understand images, and its ultimate goal is to enable computers to have the ability to recognize three-dimensional environmental information through two-dimensional images. This ability will not only enable the machine to perceive the geometric information of objects in a three-dimensional environment including shape, posture, motion, etc., but also describe, store, recognize and understand them. Camera calibration is to determine the mapping relationship from a three-dimensional space point to its two-dimensional image point, which is an essential step in many computer vision applications. In order to determine this mapping process, it is necessary to establish a geometric ...

AI Technical Summary

Problems solved by technology

But the theory and calibration method in this literature is degenerate for the case of parabolic catadioptric camera

The document "Acalibration method for paracatadioptric camera from sphere images", (DuanH., WuY., Pattern Recognition Letters, vol.33, no.6, pp.677-684, 2012) proposed a method of calibrating a parabolic catadioptric camera based on the circle point theory Linear method, but the selection of the image of the ring point in this document is more complicated

Images