A reprojection error compares an observed image point with the position predicted by projecting a reconstructed scene point through a camera model. If is an observed position and its prediction, the residual is . One possible aggregate is the per-point root mean square Euclidean norm:Coordinates in pixels give an error in pixels. Least squares instead minimizes the associated sum of squares; normalization conventions should be stated when reporting a summary.[ref]
Camera Calibration in the OpenCV-Python tutorials. Re-projection Error, projecting known points and comparing image positions
For an observation and prediction , the Euclidean norm of the residual is 5 pixels. Camera calibration can adjust model parameters to reduce many such residuals, while stereoscopic triangulation can adjust a reconstructed point with the camera parameters fixed. Low reprojection error tests agreement with observations under that model; incorrect stereo correspondence or an incorrect camera baseline can still produce wrong scene geometry.
Articles by others on the same topic
Reprojection error is a commonly used metric in computer vision, particularly in the context of camera calibration, 3D reconstruction, and stereo vision. It essentially quantifies the difference between the observed image points and the projected points obtained from a 3D model or scene representation. ### How It Works: 1. **3D Model and Camera Projection**: In a typical scenario, you have a 3D point in space and a camera model defined by intrinsic (e.g.