High-Precision Calibration of Omnidirectional Camera Using an Iterative Method
Xuanrui Gong,
Yaowen Lv,
Xiping Xu,
Zhaoguo Jiang,
Zhuang Sun
Affiliations
Xuanrui Gong
Key Laboratory of Opto-Electric Measurement and Optical Information Transmission Technology, Ministry of Education, School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun, China
Key Laboratory of Opto-Electric Measurement and Optical Information Transmission Technology, Ministry of Education, School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun, China
Xiping Xu
Key Laboratory of Opto-Electric Measurement and Optical Information Transmission Technology, Ministry of Education, School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun, China
Zhaoguo Jiang
Key Laboratory of Opto-Electric Measurement and Optical Information Transmission Technology, Ministry of Education, School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun, China
Key Laboratory of Opto-Electric Measurement and Optical Information Transmission Technology, Ministry of Education, School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun, China
A distorted checkerboard image affects the precision of omnidirectional camera calibration because of the inaccurate localization of the feature points. To solve this problem, an iterative refinement method is presented. First, the initial parameters are obtained using the traditional calibration method, and the distorted checkerboard is transformed to a distortion-free plane by the projection model that is estimated by initial parameters. Then, the feature point coordinates of the corrected image are extracted. The calibration parameters are recomputed using the refinement of new point locations until the camera parameters converge. This iterative refinement method improves the localization accuracy of feature points and, consequently, of camera calibration. The correctness and effectiveness of the method are verified by a series of simulations and physical experiments. The experiments show that the reprojection errors of feature points are reduced by 39% compared to traditional methods.
