ReprojectionError

The error \(E_{rep}\) of the 3D calibration pattern points projected into the left and right image.

It is computed as L2-norm of the individual point deviations in x and y in both images.

Let \((Lp_{i,x}, Lp_{i,y})\) and \((Rp_{i,x}, Rp_{i,y})\) be the 2D positions of the \(i_{th}\) calibration pattern point in the left and right images and \((Lp^{'}_ {i,x}, Lp^{'}_{i,y})\) and \((Rp^{'}_{i,x}, Rp^{'}_{i,y})\) the coordinates of the projection of the \(i_{th}\) calibration pattern point from the Pose into the left and right images. The reprojection error \(E_{rep}\) is then computed as:

\(E_{rep} = \sqrt{\sum[(Lp_{i,x} - Lp^{'}_{i,x})^{2} + (Lp_{i,y} - Lp^{'}_{i,y})^{2} + (Rp_{i,x} - Rp^{'}_{i,x})^{2} + (Rp_{i,y} - Rp^{'}_{i,y})^{2}]}\)

JSON Format

Type

Number

Permissions

Read-only