A Fast Neural Learning Vision System for Crowd Estimation at Underground Stations Platform

Authors:
Siu-Yeung Cho;Tommy W. S. Chow
Affiliations:
Department of Electronic Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon Tong, Hong Kong;Department of Electronic Engineering, City University of Hong Kong, Tat Chee Avenue, Kowloon Tong, Hong Kong
Venue:
Neural Processing Letters
Year:
1999

Citing 4
Cited 1

Global optimization

Global optimization
On the Problem of Local Minima in Backpropagation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distributed data fusion for real-time crowding estimation

Signal Processing
A Layer-by-Layer Least Squares based Recurrent Networks Training Algorithm: Stalling and Escape

Neural Processing Letters

A People-Counting System Using a Hybrid RBF Neural Network

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

A neural learning-based crowdestimation system for surveillance in complex scenesat the platform of underground stations is presented.Estimation is carried out by extracting a set ofsignificant features from the sequences of images.Feature indices are modeled by the neural networks toestimate the crowd density. The learning phase isbased on our proposed hybrid algorithms which arecapable of providing the global search characteristicand fast convergence speed. Promising experimentalresults were obtained in terms of estimation accuracyand real-time response capability to alert theoperators automatically.