Human shape recognition from snakes using neural networks

Ken Tabb, Stella George, Rod Adams, Neil Davey

Research output: Chapter in Book/Report/Conference proceedingPublished Conference contributionpeer-review

6 Citations (Scopus)

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') 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, and can successfully discriminate these contours based upon whether they are 'pedestrian' in shape or not.

Original languageEnglish
Title of host publicationProceedings - 3rd International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 1999
Pages292-296
Number of pages5
ISBN (Electronic)0769503004, 9780769503004
DOIs
Publication statusPublished - 1999
Event3rd International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 1999 - New Delhi, India
Duration: 23 Sep. 199926 Sep. 1999

Publication series

NameProceedings - 3rd International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 1999

Conference

Conference3rd International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 1999
Country/TerritoryIndia
CityNew Delhi
Period23/09/9926/09/99

Fingerprint

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

Cite this