Hopfield neural network for motion understanding

Author

Convertino, G. ; Brattoli, M. ; Branca, A. ; Distante, A.

Author_Institution

CNR, Bari, Italy

Volume

6

fYear

1994

fDate

27 Jun- 2 Jul 1994

Firstpage

3846

Abstract

A method for recognition of moving objects from a sequence of time-varying images is presented. The method consists of two phases: an estimation phase of optical flow (OF) field and an interpretation phase where a qualitative analysis of OF patterns is performed. The two phases interact each other in order to provide a final map in which areas of the image interested by the same motion are isolated and classified. For the estimation phase a gradient-based approach has been selected, that provides a linear optical flow map. In the interpretation phase the OF field is regarded as a 2D linear system of differential equations and hence the geometric theory of differential equations is used. The whole algorithm is implemented by means of an Hopfield neural network (HNN)

Keywords

Hopfield neural nets; differential equations; image sequences; motion estimation; object recognition; 2D linear system; Hopfield neural network; classification; differential equations; geometric theory; gradient-based approach; interpretation phase; isolation; linear optical flow map; motion understanding; moving object recognition; optical flow field estimation; qualitative analysis; time-varying image sequences; Differential equations; Geometrical optics; Hopfield neural networks; Image motion analysis; Image recognition; Linear systems; Optical computing; Pattern analysis; Performance analysis; Phase estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374824

Filename

374824