The Impact of Metrics in Mechanical Imaging

Optical flow (OF) is an alternative technique to the more classical digital image correlation (DIC) methods, able to measure the motion between two images. It is a pixel-wise method, in the sense that the displacement is defined at each pixel and its computation does not require overpixel grids. This paper examines the impact on the identified strain field, the main quantity of interest for solid mechanics, of the metrics used to quantify the conservation of the OF and to impose the regularity of the displacement. The Charbonnier and Lorentzian loss functions are inspected in this work. A new regularization approach is used to locally vary the Tikhonov parameter using a mask in order to preserve the discontinuities and encourage the appearance of local phenomena while smoothing the computed fields elsewhere. Finally, an open-source GPU-accelerated python code has been implemented.