Title :
Calibration of stereo fish-eye camera for Driver Assistance Systems
Author_Institution :
School of Computing and Mathematical Sciences, AUT and The .enpeda.. Project, The University of Auckland, New Zealand
Abstract :
The calibration of cameras in general is an essential part of setting up DAS (Driver Assistance Systems) as well as a normal maintenance procedure for which accuracy and reliability are vital. In particular, a wide field of view (e.g., by using fish-eye lenses) is of particular interest for DAS, with the additional constraint to ensure a reasonable pixel resolution. The reported work aims at identifying a suitable and accurate fish eye calibration method within the DAS context. For that purpose, three known calibration methods for fish-eye cameras have been selected, tested and compared for accuracy, reliability and ease of use within the DAS context.
Keywords :
calibration; driver information systems; image resolution; stereo image processing; DAS; driver assistance systems; eye calibration method; reasonable pixel resolution; stereo fish-eye camera; Calibration; Cameras; Lenses; Nonlinear distortion; Three dimensional displays; Vectors; Vehicles; Driver assistance; calibration; evaluation; fish eye; multiple cameras;
Conference_Titel :
Image and Vision Computing New Zealand (IVCNZ), 2010 25th International Conference of
Conference_Location :
Queenstown
Print_ISBN :
978-1-4244-9629-7
DOI :
10.1109/IVCNZ.2010.6148806