The use of neural techniques in PIV and PTV

Abstract

The neural network method uses ideas developed from the physiological modelling of the human brain in computational mechanics. The technique provides mechanisms analogous to biological processes such as learning from experience, generalizing from learning data to a wider set of stimuli and extraction of key attributes from excessively noisy data sets. It has found frequent application in optimization, image enhancement and pattern recognition, key problems in particle image velocimetry (PIV). The development of the method and its principal categories and features are described, with special emphasis on its application to PIV and particle tracking velocimetry (PTV). The application of the neural network method to important categories of the PIV image analysis procedure is described in the present paper. These are image enhancement, fringe analysis, PTV and stereo view reconciliation. The applications of common generic net types, feed-forwards and recurrent, are discussed and illustrated by example. The key strength of the neural technique, its ability to respond to changing circumstances by self-modification or regulation of its processing parameters, is illustrated by example and compared with conventional processing strategies adopted in PIV.

Implementing a Highly Parameterized Digital PIV System on Reconfigurable Hardware

“…Later he provided the theory of cross-correlation analysis [4]. Other techniques were used such as the Fourier Transform Method [5], neural networks techniques [6], the Lagrangian method [7], and recursive local-correlation [8]. PIV became a research area that depends on various engineering fields to determine the types of illumination, types of coding, types of tracer particles, types of image recording and types of interrogation.…”

Flow Visualization in Stirred Vessels

“…The calculation of the particle velocities relies on sophisticate d software. In the case of low-density images, with relatively few particles, a program identifyin g speci®c particles (`particle tracking') is suf®cient 28,29,47 ,4 8 ; for more complex¯ows, image correlation methods are used to determine the individua l particle vectors 68 , also 69,222 for a review and ®elds of application of PIV, and 33 for a comparison with particle tracking and computed tomography). The evolution of software has resulted in very detailed ow maps and even calculations of additional¯ow characteristics, e.g.…”

Stereoscopic Correspondence of Particles for 3-Dimensional Particle Tracking Velocimetry by using Genetic Algorithm

“…A hopfield neural network based computational strategy [5] was suggested by Grant and Pan [3,4]. In their approach, the camera configuration is restricted in such a way that the object plane, lens plane and image plane all need to be parallel to each other, and the lens of cameras must be in the same plane.…”