| CPC B25J 9/1692 (2013.01) [B25J 9/1697 (2013.01); G06T 7/80 (2017.01)] | 20 Claims |

|
1. A method of generating a camera model, comprising:
using a robotic assembly to move a calibration assembly relative to a camera assembly, or to move the camera assembly relative to the calibration assembly, through a series of poses to cause a calibration target to pass through at least a portion of a field of view (FOV) of the camera assembly;
using a camera of the camera assembly at the series of poses to generate a respective image of the calibration target; and
using a tracker at the series of poses to determine respective locations in space of a plurality of calibration assembly markers of the calibration assembly and respective locations in space of a plurality of camera assembly markers of the camera assembly;
generating, for each respective image, a transformation function that maps onto a three-dimensional object space features of the calibration target within the respective image.
|