View-synthesized ‘re-calibration’ of an array projector for 3D measurement from an arbitrary monocular view

Abstract

We previously presented a method on how to calibrate a high-speed Multi-Aperture Array Projector (MAAP) in order to obtain three-dimensional (3D) surface measurements using only a single camera instead of a stereo-camera configuration. The MAAP calibration procedure however can be time-consuming as it requires the camera to encode each aperture's illumination frustum by imaging the pattern incident on a depth-wise scanned test plane. This is as if recording discretized depth slices of the illumination frustums. This can be detrimental as the calibration is coupled to a single specific camera view. It would be laborious and time-consuming to repeat the entire MAAP calibration process for an alternate camera view. This study demonstrates a so-called MAAP ‘re-calibration’ solution that artificially synthesizes MAAP calibration images from an arbitrary camera view without direct imaging. This presents the opportunity to decouple the MAAP calibration from a single camera view and obtain 3D measurements from alternate camera placement setups without having to perform the entire MAAP calibration process again. This study shows that the synthesized MAAP calibration images resemble well the ground truth images. As a result, the proposed method has similar 3D measurement performance compared to when calibrating the MAAP with true images.