Binocular calibration method based on chaotic particle swarm optimization algorithm

Abstract

The invention provides a binocular calibration method based on a chaotic particle swarm optimization algorithm. A plurality of sets of dot array planar calibration board image pairs with different poses are simultaneously photographed through two image cameras. On condition that distortion is not considered, initial values of inner parameters and outer parameters of a left image camera and a right image camera are obtained by means of a Zhang's planar template linear calibration method. Then on condition that a two-order radial distortion and a two-order tangential distortion are considered, a three-dimensional reprojection error is minimized by means of the chaotic particle swarm optimization algorithm, thereby obtaining final inner parameter and final outer parameter of the two image cameras. In an iteration optimization process, a global adaptive inertia weight (GAIW) is introduced. A particle local neighborhood is constructed by means of a dynamic annular topological relationship. Speed and current position are updated according to an optimal fitness value in the particle local neighborhood. Furthermore chaotic optimization is performed on the optimal position which corresponds with the optimal fitness value in the particle local neighborhood. The binocular calibration method effectively settles a problem of low calibration precision caused by a local extreme value in a previous particle swarm optimization algorithm, thereby improving binocular calibration precision and ensuring high precision in subsequent binocular three-dimensional reconstruction.

Description

technical field [0001] The invention relates to the field of machine vision measurement, in particular to a dual-objective calibration method based on a chaotic particle swarm optimization algorithm. Background technique [0002] Binocular vision is the most important distance perception technology in the passive distance measurement method. Because it directly simulates the processing method of human vision on the scene, two cameras can be used to shoot the measured object from different angles at the same time. After binocular positioning and stereo matching, The three-dimensional information of the object is obtained by using the principle of triangulation. Among them, binocular positioning is the most important part of binocular vision, and its essence is to determine the internal parameters of the two cameras and the relative pose relationship between the two cameras according to the geometric imaging model of the cameras. [0003] The existing camera calibration metho...

AI Technical Summary

Problems solved by technology

[0003] The existing camera calibration methods mainly include linear method, two-step method, nonlinear optimization method, etc. Among them, the linear method does not consider lens distortion, and the accuracy is not high; The methods mainly include Tsai’s two-step method and Zhang’s planar template method, both of which solve the initial parameters linearly, and then perform nonlinear optimization considering distortion, but still cannot meet the requirements of industrial machine vision, and the calibration accuracy has improved; The nonlinear optimization method can obtain higher calibration accuracy due to multiple iterative optimizations considering distortion

Traditional nonlinear parameter optimization methods include Levenberg-Marquardt method, gradient descent method, conjugate gradient method, Newton method, etc., but the calculation process of these methods is complex, sensitive to the initial iteration value, parameters are constrained by nonlinear factors, and converge Poor performance, easy to fall into local optimum, difficult to obtain optimal solution

Many scholars have proposed the use of intelligent optimization algorithms for nonlinear calibration. Among them, the particle swarm optimization algorithm is widely used in parameter optimization in camera calibration due to its advantages of easy implementation, high precision, and fast convergence. However, it is easy to fall into local extreme values, resulting in inaccurate calibration results.

Images