Performance of Background Oriented Schlieren with different background patterns and image processing techniques

Abstract

Synthetic tests of the accuracy, spatial resolution and robustness with respect to large gradient of the apparent displacement are performed for Background Oriented Schlieren (BOS) measurements using various background patterns and image processing techniques, including multi-pass cross-correlation, iterative Horn–Schunck and Lucas–Kanade optical flow algorithms and Fourier Transform Profilometry (FTP). It is shown that FTP with periodic sinusoidal or binary fringe pattern outperforms all the other methods. With optimal pattern period λpattern=6−15pix it is able to resolve perturbations with wavelength down to λpattern2 and to obtain reliable results for images with displacement gradient up to 0.9 pix/pix. Better performance of FTP, compared to multi-pass cross-correlation, is confirmed for real experimental measurements of water temperature in natural convection near a heated vertical plate. FTP advantages and limitations, including possible nonlocal error, associated with phase unwrapping, are discussed.