New tracking technique for Particle Image Velocimetry using artificial neural network
Academic Article
Overview
Additional Document Info
View All
Overview
abstract
The analysis of Particle Image Velocimetry (PIV) data requires the use of effective algorithms to efficiently track the particles suspended in the fluid flow. The method described presents a new approach to the problem through the use of an artificial neural network algorithm. Contrary to the classic cross correlation method, this new method does not require a large number of particles per frame, can handle flows with large velocity gradients and is suited for tracking images with multiple exposures as well as tracking through consecutive images. The algorithm was tested on synthetic data, to provide a thorough performance analysis.