A trainable vision-based system is presented, which is able to perform reliable, real time estimates of the crowding level present on the platforms of underground stations. Taking as input standard, b/w images of the scene, a classification of the crowding level is returned in terms of five qualitative crowding classes, ranging from no people to overcrowding. Visual feature extraction and fuzzy classification methods employed are described in detail, as well as the procedure adopted to train the Hyper Basis Function neural classifier. Experiments and results are also reported as obtained on real data, with some emphasis on the possibility of empirically estimating the generalization capability of the proposed system
A Fuzzy Classifier for Visual Crowding Estimates
Boninsegna, Massimo;Caprile, Bruno Giovanni
1996-01-01
Abstract
A trainable vision-based system is presented, which is able to perform reliable, real time estimates of the crowding level present on the platforms of underground stations. Taking as input standard, b/w images of the scene, a classification of the crowding level is returned in terms of five qualitative crowding classes, ranging from no people to overcrowding. Visual feature extraction and fuzzy classification methods employed are described in detail, as well as the procedure adopted to train the Hyper Basis Function neural classifier. Experiments and results are also reported as obtained on real data, with some emphasis on the possibility of empirically estimating the generalization capability of the proposed systemI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
