Camera Calibration with Varying Parameters Based On Improved Genetic Algorithm

摘要

In this paper, we propose an approach based on improved genetic algorithms for the camera calibration having the varying parameters. The present method is based on the formulation of a nonlinear cost function from the determination of the relationship between points of the image planes and all parameters of the cameras. The minimization of this function by a genetic approach enables us to simultaneously estimate the intrinsic and extrinsic parameters of different cameras. Comparing to traditional optimization methods, the camera calibration based on improved genetic algorithms can avoid being trapped in a local minimum and does not need the initial value. The proposed technique to find the near optimal solution without the need for initial estimates of the cameras parameters. Tested on several cases, the proposed method proved to be an effective tool to determine the camera parameters necessary for various applications, such as the images rectification, the analytical photogrammetry and 3D reconstruction from 2D images.