Human shape recognition from snakes using neural networks

Ken Tabb, N. Davey, S. George, R.G. Adams

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)
81 Downloads (Pure)

Abstract

This paper documents experiments which have been carried out with several neural network systems designed to categorise pedestrian shapes from non-pedestrian shapes. Active Contour models (‘Snakes’) [1] have been used to obtain contours of pedestrians as they move around the visual field. Neural networks have then been trained on representations of these relaxed snakes. The neural network systems developed can successfully discriminate these contours based upon whether they are ‘pedestrian’ in shape or not. Results are presented along with a discussion of some of the system’s possible applications.
Original languageEnglish
Title of host publicationIn: Procs 3rd Int Conf on Computational Intelligence and Multimedia Applications (ICCIMA'99)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages292-296
ISBN (Print)0-7695-0300-4
DOIs
Publication statusPublished - 1999

Fingerprint

Dive into the research topics of 'Human shape recognition from snakes using neural networks'. Together they form a unique fingerprint.

Cite this