DocumentCode
3064933
Title
A multilayer massively parallel architecture for optical flow computation
Author
Colombo, C. ; Del Bimbo, A. ; Santini, S.
Author_Institution
Dipartimento di Sistemi e Inf., Firenze Univ., Italy
fYear
1992
fDate
30 Aug-3 Sep 1992
Firstpage
209
Lastpage
213
Abstract
A two-layers architecture for optical flow computation is presented, which uses neural nets in the lower layer and a special relaxation system in the upper layer. The high degree of parallelism of the architecture makes it particularly suitable for real-time applications
Keywords
feedforward neural nets; image processing equipment; image sequences; motion estimation; parallel architectures; real-time systems; special purpose computers; 5 layer neural network spatial gradient; brightness; multilayer perceptrons; neural nets; optical flow computation; real-time applications; special relaxation system; two-layers architecture; Biomedical optical imaging; Computer architecture; Concurrent computing; Image motion analysis; Neural networks; Nonhomogeneous media; Optical computing; Optical devices; Optical network units; Parallel architectures;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1992. Vol. IV. Conference D: Architectures for Vision and Pattern Recognition, Proceedings., 11th IAPR International Conference on
Conference_Location
The Hague
Print_ISBN
0-8186-2925-8
Type
conf
DOI
10.1109/ICPR.1992.202168
Filename
202168
Link To Document