An automatic and robust chessboard corner extraction

Authors:
Xifan Shi;Ning Hong;Tiefeng Cai
Affiliations:
Zhijiang College, Zhejiang University of Technology, Hangzhou, China;Zhijiang College, Zhejiang University of Technology, Hangzhou, China;Zhijiang College, Zhejiang University of Technology, Hangzhou, China
Venue:
Transactions on edutainment VI
Year:
2011

Citing 5
Cited 0

A Flexible New Technique for Camera Calibration

IEEE Transactions on Pattern Analysis and Machine Intelligence
Camera Self-Calibration: Theory and Experiments

ECCV '92 Proceedings of the Second European Conference on Computer Vision
Performance of Constraint Based Pose Estimation Algorithms

Mustererkennung 2000, 22. DAGM-Symposium
A Four-step Camera Calibration Procedure with Implicit Image Correction

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Pseudo-linearizing collinearity constraint for accurate pose estimation from a single image

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Camera calibration is crucial in many applications. Our lab uses the world wide used camera calibration toolbox for Matlab and finds its two major drawbacks, i.e., manual selection of the four extreme corners and inability to process images larger than 2MP. In this paper, a new method to eliminate these drawbacks is presented. The original chessboard is modified slightly and based on the added boundary composed of four narrow rectangles, the four extreme corners can be forecast. In addition, because it is implemented by C++, the 2MP limitation no longer exists. The experiment shows that even without multithread optimization and even for a 50MP photo, the corners can be extracted within 20 seconds on a 3GHz CPU.