TY - GEN
T1 - Human shape recognition from snakes using neural networks
AU - Tabb, Ken
AU - George, Stella
AU - Adams, Rod
AU - Davey, Neil
N1 - Publisher Copyright:
© 1999 IEEE.
PY - 1999
Y1 - 1999
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=49249125850&partnerID=8YFLogxK
U2 - 10.1109/ICCIMA.1999.798545
DO - 10.1109/ICCIMA.1999.798545
M3 - Published Conference contribution
AN - SCOPUS:49249125850
T3 - Proceedings - 3rd International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 1999
SP - 292
EP - 296
BT - Proceedings - 3rd International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 1999
T2 - 3rd International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 1999
Y2 - 23 September 1999 through 26 September 1999
ER -