Precision distortion correction technique based on FOV model for wide-angle cameras in automotive sector - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 462

information recording, parking assistance, safe driving, and the prevention of traffic accidents.
Such systems record all details of the surrounding areas using an ultra-wide-angle lens (190°)
with high resolution. In order to use such images, distortion correction is necessary to enable
users to monitor these images.
This chapter proposed a distortion correction method for a camera model in which the dis-
tortion center correction method was optimized using the FOV model, and distortion cen-
ter was found using 2D paterns. Through the proposed method, complete distortion correc-
tion can be achieved in the vertical and horizontal directions so that images without size and
pattern distortion can be used for image processing, image recognition, and monitoring by
users. In general, cameras for AVM systems use high-precision center point estimation. Our
algorithm can produce high quality and minimum error of AVM top views from images ac-
quired from inexpensive cameras.
References
[1] Heikkila J. Geometirc camera calibration using circular control points. IEEE Trans Pat-
tern Anal Mach Intell. 2000;22(19):1066-1077.
[2] Kim W, Baik YK, Lee KM. A parameter-free radial distortion correction of wide angle lenses
using distorted vanishing points. In: 14th Japan-Korea Joint Workshop on Frontiers of
Computer Vision (FCV); 2008:53-58 (1).
[3] Jo YK. Barrel distortion compensation of fisheye lens for automotive omnidirectional camera
module system. Dongguk University; 2010 Master's thesis of.
[4] Devernay F, Faugeras O. Straight lines have to be straight-automatic calibration
and removal of distortion from scenes of structured environments. Mach Vision Appl.
2001;13(1):14-24.
[5] Thorsten T, Hellward B. Automatic line-based estimation of radial lens distortion. In-
tegr Comput Aided Eng. 2005;12(2):177-190.
[6] Kim BK, Chung SW, Song MK, Song WJ. Correcting radial lens distortion with advanced
outlier elimination. In: IEEE International Conference on Audio, Language and Image
Processing (ICALIP); 2010:1693-1699.
[7] Wang A, Qiu T, Shao L. A simple method of radial distortion correction with centre
of distortion estimation. J Math Imaging Vision. 2009;35(3):165-172.
[8] Shah S, Aggarwal J. Intrinsic parameter calibration procedure for a (higher distortion)
fisheye lens camera with distortion model and accuracy estimation. Patern Recogn.
1996;29(11):1775-1788.
[9] Chao T-w. Wide-scoped top-view monitoring and image-based parking guiding,
Master's Thesis; 2009.
[10] Harris C, Stephens MJ. A combined corner and edge detector. In: Alvey Vision Conferen-
ce; 1988:147-152.
[11] Zhang Z. A flexible new technique for camera calibration. IEEE Trans Patern Anal
Mach Intell. 2000;22(11):1330-1334.