Bulpitt, A. J. and Allinson, N. M. (1991) Motion perception and recognition using moving light displays. In: Second International Conference on Artificial Neural Networks, 18-20 November 1991, Bournemouth.

PDF 00140292.pdf - Whole Document Restricted to Repository staff only Download (229Kb) | Request a copy

Abstract

Despite the limited amount of information that is available to the observer of a moving light display, humans are able to infer detailed information about the activity and identity of the actors within the film. The development of a system, which uses such displays to recognise different types of human motion, is described using a spatio-temporal neural network to classify different temporal sequences of movement. ART architectures are employed to adapt and maintain the learned codes of the network providing real-time learning and stability against insignificant events

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	Despite the limited amount of information that is available to the observer of a moving light display, humans are able to infer detailed information about the activity and identity of the actors within the film. The development of a system, which uses such displays to recognise different types of human motion, is described using a spatio-temporal neural network to classify different temporal sequences of movement. ART architectures are employed to adapt and maintain the learned codes of the network providing real-time learning and stability against insignificant events
Keywords:	Neural nets, Pattern recognition
Subjects:	G Mathematical and Computer Sciences > G730 Neural Computing G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Tammie Farley
Date Deposited:	20 Apr 2012 11:48
Last Modified:	13 Mar 2013 09:06
URI:	http://eprints.lincoln.ac.uk/id/eprint/5032

Actions (login required)

View Item