Intelligent optimization-based camera calibration method

Abstract

The invention discloses an intelligent optimization-based camera calibration method, which comprises the following steps of: obtaining pixel coordinates of feature points of an image by adopting a harris sub-pixel angular point extraction method; calculating the initial values of internal and external parameters according to the pixel coordinates of the image and corresponding coordinates in the world coordinate system; initializing a particle swarm, randomly generating d particles evenly distributed around the initial values, and forming an i*d dimensional particle swarm matrix; taking an initial particle swarm as a current-generation optimal local matrix, calculating the fitness functions of particles of the initial particle swarm, and selecting and taking a particle with the minimal fitness value as the optimal particle; and renewing the particle swarm, calculating the fitness values of the new particle swarm, comparing and replacing with the previous-generation optimal local matrix, obtaining a new-generation optimal local matrix, then, obtaining a new optimal particle, and meanwhile, calculating and renewing the values of external parameters (R and T). The intelligent optimization-based camera calibration method has the advantages that: a quantum particle swarm intelligent optimization algorithm is introduced into camera calibration; and the accuracy is higher, the calculation of the initial values is simple, and the convergence rate is fast.

Description

technical field [0001] The invention relates to a camera calibration method based on intelligent optimization, and relates to a robot vision calibration technology. Background technique [0002] One of the basic tasks of computer vision is to calculate the geometric information of the object in the three-dimensional space from the image information obtained by the camera, and then reconstruct and recognize the object, and the three-dimensional geometric position of a point on the surface of the space object and its corresponding point in the image The interrelationship of is determined by the geometric model of camera imaging, and these geometric model parameters are camera parameters. Under most conditions, these parameters must be obtained through experiments and calculations, and this process is called camera calibration (or calibration). The calibration process is to determine the geometric and optical parameters of the camera, and the orientation of the camera relative...

AI Technical Summary

Problems solved by technology

[0004] The traditional calibration method mainly uses the iterative optimization method in the least squares method, which has many shortcomings, such as sensitivity to initial values, poor convergence, and easy to fall into local optimal solutions, etc.

In addition, there is no general-purpose camera calibration program package for occasions that require high-precision camera parameters. Each of them designs a calibration program for the experimental platform, which is time-consuming and laborious.

Images