Title :
Velocity measurement of granular flow with a Hopfield network
Author :
Lee, Jingeol ; Principe, Jose C. ; Hanes, Daniel M.
Author_Institution :
Dept. of Electr. Eng., Florida Univ., Gainesville, FL, USA
fDate :
31 Aug-2 Sep 1995
Abstract :
The transport of granular flow is common to many industrial processes. This paper discusses a methodology to measure the velocity of dry granular solids down an inclined chute using high speed digital images. Acrylic particles have been used as granular solids in our experiment. First, particles are located using normalized correlation. A technique for measuring the velocities of individual acrylic particles is developed based on a Hopfield network to solve the particle correspondence problem between successive images. A new, rigidity constraint is applied to the Hopfield energy function, and the results show better performance than the conventional cost function
Keywords :
Hopfield neural nets; channel flow; correlation methods; granular materials; motion estimation; neural nets; two-phase flow; velocity measurement; Hopfield energy function; Hopfield network; acrylic particles; granular flow; high-speed digital images; inclined chute; industrial processes; normalized correlation; rigidity constraint; velocity measurement; Brightness; Conducting materials; Cost function; Digital images; Material storage; Particle measurements; Pattern recognition; Sea measurements; Solids; Velocity measurement;
Conference_Titel :
Neural Networks for Signal Processing [1995] V. Proceedings of the 1995 IEEE Workshop
Conference_Location :
Cambridge, MA
Print_ISBN :
0-7803-2739-X
DOI :
10.1109/NNSP.1995.514912
