MATLAB Camera Calibration with a Checkerboard: Board Size, the Even/Odd Rule, and the Calibrator App
MATLAB’s Camera Calibrator app calibrates from a checkerboard, but it is stricter than OpenCV: it needs a board with an even number of squares on one edge and an odd number on the other, which produces two black and two white corners so the app can fix orientation and origin. Board size is counted in squares (points are the interior corners), plus the detectCheckerboardPoints / generateCheckerboardPoints / estimateCameraParameters workflow, stereo and fisheye, and why the target sets the accuracy ceiling.
HALCON Calibration Plate: CALTAB Dot-Mark Targets, Geometry, and Description Files
HALCON calibrates from a plate of circular marks, not a checkerboard. The plate geometry is defined by a description file, the marks are fit as ellipses with perspective-bias correction, and a finder pattern fixes the origin. How the CALTAB workflow works, classic fully-visible versus newer partial-view plates, why a third-party plate needs a matching description file, substrate and accuracy from ±0.5 µm, and the VME-series models.
Best Checkerboard Size for OpenCV Camera Calibration: Squares, Square Size, and Board Dimensions
In OpenCV, three choices decide checkerboard calibration quality: the inner-corner count you pass to findChessboardCorners (equal to squares minus one), the physical square size relative to working distance, and overall board size and flatness. How to pick each, a recommended starting configuration, the feature-count-versus-images trade-off, and when a plain checkerboard is the wrong pattern.
Camera Calibration Pattern Types: Checkerboard, ChArUco, Dot Grid, and AprilGrid Compared
A calibration pattern gives a camera a field of reference points with known geometry. The families differ in feature type (corner, centroid, coded marker), whether points are individually identified, and which software expects them. Overview of checkerboard, ChArUco, dot/circle grid and AprilGrid, how to choose by toolchain and application, and why the substrate sets the accuracy ceiling.
Checkerboard vs Dot Grid Calibration Targets: Corner Detection, Centroid Bias, and How to Choose
A checkerboard is detected by its corners (saddle points); a dot grid by the centroids of its dots. Corners are projectively invariant — no systematic offset under perspective; dot centroids are lower-noise and denser but carry a perspective/eccentricity bias unless the detector models the ellipse. What that means for accuracy, which software expects which pattern, substrate accuracy from ±0.5 µm, and how to choose.
ChArUco Calibration Boards: Coded-Marker Targets for Partial-View and Multi-Camera Calibration
A ChArUco board is a checkerboard with coded ArUco markers in its white squares — sub-pixel corners plus a unique ID at each one, so calibration succeeds even when the board is tilted, occluded or only partly in frame. What it is, why it beats a plain checkerboard, the four specs that matter, how to choose a configuration and substrate, how it differs from AprilGrid, and how to order the right target.
OpenCV/Checkerboard Camera Calibration Targets: Essential Tools for Precision Machine Vision
OpenCV/Checkerboard Calibration Targets enable precise camera calibration for industrial vision systems, correcting lens distortion and ensuring measurement accuracy. Available in various materials and sizes, these targets are essential tools for manufacturing, robotics, and quality inspection applications.