Abstract
This work describes a novel approach to localize sub-pixel chessboard corners for camera calibration and pose estimation. An ideally continuous chessboard corner model is established, as a function of corner coordinates, rotation and shear angles, gain and offset of grayscale, and blurring strength. The ideal model is evaluated by a low-cost and high-similarity approximation for sub-pixel localization, and by performing a nonlinear fit to input image. A self-checking technique is also proposed by investigating qualities of the model fits, for ensuring the reliability of addressing perspective-n-point problem. The proposed method is verified by experiments, and results show that it can share a high performance. It is also implemented and examined in a common vision system, which demonstrates that it is suitable for on-site use.
Highlights
Computer vision is an interdisciplinary field that deals with how computers can be made for gaining high-level understanding from digital images or videos
In order to decrease the influence on localization result due to different parameter settings, for both the proposed and referenced localization result due to different parameter settings, for both the proposed and referenced methods, methods, each chessboard corner is detected with the same initial pixel coordinates, and refined each chessboard corner is detected with the same initial pixel coordinates, and refined from the same from the same local neighborhood with a square size of 31 × 31 pixels
The proposed approach is based on an ideal chessboard model, established as a function of corner coordinates, rotation and shear angles, gain and offset of grayscale, and blurring strength
Summary
Computer vision is an interdisciplinary field that deals with how computers can be made for gaining high-level understanding from digital images or videos. As a sub-domain of computer vision, visual measurement is employed for some applications involving dimensional survey tasks, and it always utilizes one or more cameras with exactly known intrinsic parameters for addressing perspective-n-point problem [1] and, camera calibration is pivotal for ensuring the system accuracy [2]. Most camera calibration approaches require a certain number of correspondences between world and image frames, which are known as control points, and they usually are called “targets”. These approaches are performed with planar or non-planar targets with exactly known geometries. After the targets are photographed, their corresponding image points need to be localized for solving intrinsic and extrinsic parameters based on bundle adjustment or other optimization models [4]. The accuracy of camera calibration is largely dependent on the localization of image points, and usually evaluated by re-projection errors [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
