(Camera) Calibration Wizard; today's reading.

camera-calibration optimization today-i-read

  1. Songyou Peng and Peter Sturm, “Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty,” in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), Oct. 2019, pp. 1497–1505, doi: 10.1109/ICCV.2019.00158 [Online]. Available at: https://ieeexplore.ieee.org/document/9009540/. [Accessed: October 20, 2024]

    tl;dr: Uses three freely-acquired poses to initialize, creates an optimization problem for the next pose such that the expected uncertainty of the intrinsic camera parameters is minimized. The process is to formulate the calibration problem as geometric reprojection error, and Jacobian matrices are computed. The data is extended to a hypothetical next pose, the next pose and intrinsic parameters are parameterized within the Jacobian. Through some matrix transformations, the covariance matrix of the intrinsic parameters can be extracted using the Jacobian. Corner uncertainty is incorporated, as poses that reduce uncertainty may be perpendicular to the image plane and be unusable. Code is available but in Matlab.

© Amy Tabb 2018 - 2026. All rights reserved. The contents of this site reflect my personal perspectives and not those of any other entity.