Sign In

Communications of the ACM

ACM TechNews

Algorithm Can Infer Velocity, Pressure from Video of Fluid Flows

View as: Print Mobile App Share:
A video showing smoke traveling around an airfoil.

An algorithm developed by researchers at Brown University can determine the velocities and pressures of a fluid flow by analyzing a video of it.

Credit: News from Brown

Researchers at Brown University have developed a computer algorithm that can determine the velocities and pressures of a fluid flow by analyzing video of the flow.

The researchers say the method could be used to analyze magnetic resonance imaging (MRI) data of blood flow through a brain aneurysm, and compute the stress being placed on an arterial wall by the flow.

In addition, the technique could be used to calculate wind speeds and barometric pressures from satellite imagery of hurricanes, or to calculate forces on vehicles in wind tunnel experiments, according to the researchers.

The technique relies on artificial neural networks coded with Navier Stokes equations, partial differential equations that describe the flow of incompressible fluids.

The system inputs video data showing the movement of a passive scaler; the neural networks use that data to derive values for quantities of "hidden" variables.

From News from Brown
View Full Article


p>Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA



No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account