	US 12,205,329 B1
	Calibration for multi-camera and multisensory systems
Tarek El Dokor, Phoenix, AZ (US); Jordan Cluster, Tempe, AZ (US); and Milind Subhash Gide, Phoenix, AZ (US)
Assigned to Edge 3 Technologies, Phoenix, AZ (US)
Filed by Edge 3 Technologies, Inc., Phoenix, AZ (US)
Filed on Dec. 18, 2023, as Appl. No. 18/542,919.
Application 18/542,919 is a continuation of application No. 18/103,437, filed on Jan. 30, 2023, granted, now 11,900,636.
Application 18/103,437 is a continuation of application No. 16/175,754, filed on Oct. 30, 2018, granted, now 11,568,568, issued on Jan. 31, 2023.
Claims priority of provisional application 62/579,813, filed on Oct. 31, 2017.
Int. Cl. G06T 7/80 (2017.01); G06T 7/593 (2017.01)

CPC G06T 7/85 (2017.01) [G06T 7/593 (2017.01)]

6 Claims

1. A method for calibrating an image capture device, comprising:

capturing one or more Multiview image sets by the image capture device;

detecting one or more calibration features in each image set by a processor;

initializing each of a one or more calibration parameters a corresponding default value;

converting one or more 2D features to 3D;

computing a Euclidian distance between one or more of two or more pairs of 3D features;

computing a difference between each computed Euclidian distance and a ground truth as a dimensioning error; reprojecting one or more 3D features to 2D;

computing the reprojection error for one or more of the reprojected features;

aggregating the dimensioning errors and the reprojection errors

determining if the aggregated errors have been minimized;

adjusting the calibration parameters if it is determined that that the combination of the aggregated errors has not been minimized; and

returning to the step of converting one or more 2D features to 3D.