DocumentCode :
276631
Title :
Real-time early vision neurocomputing
Author :
Fay, David A. ; Waxman, Allen M.
Author_Institution :
Cognitive & Neural Syst. Program, Boston Univ., MA, USA
Volume :
i
fYear :
1991
fDate :
8-14 Jul 1991
Firstpage :
621
Abstract :
Summarizes recent work on real-time implementations of early vision neural computations on the PIPE video-rate parallel computer. PIPE is an eight-stage machine for real-time image processing, performing nearly one billion 8-bit operations per second. Temporal computations are implemented using the integral solutions of the differential equations that govern the neurodynamics via an exponentially fading memory. Spatial computations are performed by convolving the images with masks. Dynamic neural networks that perform light adaptation, spatial contrast enhancement, and image feature velocity extraction have been implemented to process live imagery (256×256 pixels, 8-bit data) at 30 frames/sec. These computations simulate spatiotemporal processing in the retina and the motion pathway of the brain. Some examples of these computations are described
Keywords :
brain models; computer vision; neural nets; parallel processing; real-time systems; 256 pixel; 65536 pixel; 8 bit; PIPE; brain; convolution; differential equations; dynamic neural nets; early vision neurocomputing; exponentially fading memory; image feature velocity extraction; image processing; light adaptation; masks; motion pathway; neurodynamics; real-time implementations; retina; spatial computations; spatial contrast enhancement; spatiotemporal processing; temporal computations; video-rate parallel computer; Biological neural networks; Computer vision; Concurrent computing; Data mining; Differential equations; Fading; Feature extraction; Image processing; Integral equations; Neurodynamics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
Type :
conf
DOI :
10.1109/IJCNN.1991.155250
Filename :
155250
Link To Document :
بازگشت