Intel Corporation
CAMERA CALIBRATION USING DEPTH DATA

Abstract:

An example system disclosed herein includes a camera to: capture a first image set of a first view of an object when the camera is in a first position, the first image set including first infrared data and first RGB data; capture a second image set of a second view of the object when the camera is in a second position, the second image set including second infrared data and second RGB data; and capture a third image set of a third view of the object when the camera is in a third position, the third image set including third infrared data and third RGB data. The example system also includes at least one processor to: identify a plurality of features among the first view, the second view, and the third view; align the second view relative to the first view by using one or more of the features; align the third view relative to the first view by using one or more of the features; determine first three-dimensional data from the first infrared data; determine second three-dimensional data from the second infrared data; determine third three-dimensional data from the third infrared data; average the first three-dimensional data, the second three-dimensional data, and the third three-dimensional data; create a calibration model based on the average; determine a refined view based on the calibration model; and compute a three dimensional to two dimensional projection based on the refined view.