revised_manuscript_20180502.pdf (3.63 MB)
Automatic checkerboard detection for camera calibration using self-correlation
journal contribution
posted on 2019-02-21, 11:36 authored by Y Yan, P Yang, L Yan, J Wan, Y Sun, K Tansey, A Asundi, H ZhaoThe checkerboard is a frequently-used pattern in camera calibration, an essential process to get
intrinsic parameters for more accurate information from images. An automatic checkerboard detection method
that can detect multiple checkerboards in a single image is proposed in this paper. It contains a corner extraction
approach using self-correlation and a structure recovery solution using constraints related to adjacent corners
and checkerboard block edges. The method utilizes the central symmetric feature of the checkerboard crossings
as well as the spatial relationship of neighboring checkerboard corners and the grayscale distribution of their
neighboring pixels. Five public datasets are used in the experiments to evaluate the method. Results show high
detection rates and a short average runtime of the proposed method. In addition, the camera calibration accuracy
also presents the effectiveness of the proposed detection method with re-projected pixel errors smaller than 0.5
pixels.
Funding
This work was supported by the National Natural Science Foundation of China [grant number 41571432]; the National Key Research and Development Program of China [grant number SQ2017YFGX040110]; the National Key Research and Development Program of China [grant number 2017YFB0503004]; the State Administration of Foreign Experts Affairs program of China [grant number GDT0161100077].
History
Citation
Journal of Electronic Imaging, 2018, 27 (3), 033014Author affiliation
/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/School of Geography, Geology and the Environment/GIS and Remote SensingVersion
- AM (Accepted Manuscript)