Title :
A coupled-grid neural network retina for real-time visual processing
Author :
De Yong, M. ; Eskridge, Thomas ; Palmer, Alan
Author_Institution :
New Mexico State Univ., La Cruces, NM, USA
Abstract :
A real-time parallel retinal processor is currently being developed. The processor is based on a hybrid analog/digital neural processing element. The processor uses spatiotemporal characteristics of its input images to perform feature enhancement and extraction, motion detection and velocity measurements, target tracking, and system focal length adjustments. The subsystems which perform the four operations are described
Keywords :
computer vision; feature extraction; hybrid computers; image processing; image sensors; motion estimation; neural nets; parallel architectures; real-time systems; tracking; coupled-grid neural network retina; feature enhancement; machine vision; motion detection; parallel retinal processor; real-time visual processing; system focal length adjustments; target tracking; velocity measurements; Computer vision; Concurrent computing; Feature extraction; Motion detection; Neural networks; Neurons; Retina; Shape; Target tracking; Velocity measurement;
Conference_Titel :
Circuits and Systems, 1992., Proceedings of the 35th Midwest Symposium on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-0510-8
DOI :
10.1109/MWSCAS.1992.271158
