CAMERA CALIBRATION USING NEURAL NETWORKS
Márcio Mendonça
Department of Electrical Technology
Federal Center of Technology and Education
86300-000, Cornelio Procópio, PR
Brazil
marcio_mendonca@zipmail.com.br
Ivan N. da Silva, José E. C. Castanho
Department of Electrical Engineering
School of Engineering, São Paulo State University, CP. 473
17015-970, Bauru, SP
Brazil
ivan|castanho@feb.unesp.br http://www.feb.unesp.br
ABSTRACT
This work presents a procedure for camera calibration using artificial neural networks of the type back propagation perceptron. Camera calibration is employed in computer vision for pose determination and it requires a solution of non-linear system of equations. By employing neural network, it becomes unnecessary to know the parameters of the cameras, such as focus, distortions besides the geometry of the system. Camera simulations and real experiments are used to demonstrate and evaluate the procedure.
Keywords: Computer vision, camera calibration, neural networks, and stereo vision.