"

Cookies ussage consent

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

I agree, do not show this message again.

CAMERA CALIBRATION USING COMPOUND GENETIC-SIMPLEX ALGORITHM

G. G. Savii1,*

Affiliation

  1. “Politehnica” University of Timisoara, Faculty of Mechanical Engineering, Department of Mechatronics, 1 Mihai Viteazul Blvd., 300222 Timisoara, Romania

Abstract

The paper presents a novel camera calibration method using a two-step approach. First, a genetic algorithm is used to find a good enough approximation of the solution. Then a multidimensional unconstrained nonlinear minimization (Nelder-Mead simplex) algorithm is used to refine the solution. This approach avoids errors due to linearizations and automatically finds a very good initial point for the error minimizing procedure. All the camera parameters (intrinsic and extrinsic) are determined simultaneously, giving a consistent solution. Tested on several cases, the proposed method proved to be an efficient tool for determining the camera parameters needed for various applications, like analytical photogrammetry, 3-D space reconstruction from 2-D images and vision-based head tracking..

Keywords

Camera calibration, Genetic algorithm, Simplex algorithm.

Submitted at: Sept. 9, 2004
Accepted at: Dec. 6, 2004

Citation

G. G. Savii, CAMERA CALIBRATION USING COMPOUND GENETIC-SIMPLEX ALGORITHM, Journal of Optoelectronics and Advanced Materials Vol. 6, Iss. 4, pp. 1255-1261 (2004)