Multiscale Adaptive Correlation Method for Ultrasound Speckle Image Velocimetry

In this paper, we introduce and evaluate a multiscale correlation-based image velocimetry approach to the estimation of in-plane displacements of ultrasound speckles. The method replaces the conventional rectangular interrogation window by a smooth Gaussian weight function and locally adapts its shape and orientation to estimated velocities by evaluating a corresponding criterion. Furthermore, displacements are continuously refined which improves the sub-pixel accuracy of the computed velocities. Experimental results are reported that we obtained by applying the method to the SA-VFI challenge datasets.