A single-image ct machine room surveillance camera calibration method

Abstract

The invention discloses a single-image CT (computed tomography) machine room camera calibration method. The method includes: using a camera to be calibrated to photograph a regular solid object with known structure to acquire an image; according to structural characteristics of the regular solid object, acquiring three-dimensional world coordinates of a plurality of angular points and corresponding two-dimensional image coordinates; applying the two-dimensional image coordinates and three-dimensional world coordinates of each angular point to a camera model, performing first iterative optimization solving by means of iterative optimization of set initial values so as to obtain first inside and outside camera parameters; according to the structural characteristics of the regular solid object, acquiring three-dimensional world coordinates of a plurality of equally-divided discrete points and corresponding two-dimensional image coordinates; applying the two-dimensional image coordinates and three-dimensional world coordinates of each equally-divided discrete point to the camera model, performing second iterative optimization solving by means of iterative optimization using the first inside and outside camera parameters as initial values, and thus acquiring precise inside and outside camera parameters.

Description

technical field [0001] The invention relates to the technical field of computer vision detection, in particular to a method for calibrating a monitoring camera in a single-image CT machine room. Background technique [0002] In computer vision applications, in order to obtain the correspondence between image pixels and actual physical space points, camera calibration is an essential process. Camera calibration, under the assumed camera model, uses the images captured by the camera to restore objects in space. After image processing, a series of mathematical transformations and calculation methods are used to obtain the internal geometric and optical characteristics of the camera (that is, internal parameters), as well as the positional relationship between the camera coordinate system and the spatial coordinate system (that is, external parameters). [0003] 1) Internal parameters include f, (Cx, Cy), k1, sx, where: [0004] f: focal length, in millimeters; [0005] (Cx,C...

AI Technical Summary

Problems solved by technology

[0033] When using the calibration method based on active vision, the camera must be controlled to do some special motion, but in most cases it is difficult to know the motion state of the camera, or the motion state of the camera is simply impossible to know, in these cases, it cannot be used Calibration method based on active vision

[0034] When using the self-calibration method: since the calibration is performed on the premise that the internal parameters have not changed and the corresponding relationship between the image points has been determined, the calibration accuracy is poor and the stability is not very good, and when the internal parameters change can not be used

Images