A neural-based crowd estimation by hybrid global learning algorithm

Author

Cho, Siu-Yeung ; Chow, Tommy W S ; Leung, Chi-Tat

Author_Institution

Dept. of Electron. Eng., City Univ. of Hong Kong, Kowloon, Hong Kong

Volume

29

Issue

4

fYear

1999

fDate

8/1/1999 12:00:00 AM

Firstpage

535

Lastpage

541

Abstract

A neural-based crowd estimation system for surveillance in complex scenes at underground station platform is presented. Estimation is carried out by extracting a set of significant features from sequences of images. Those feature indexes are modeled by a neural network to estimate the crowd density. The learning phase is based on our proposed hybrid of the least-squares and global search algorithms which are capable of providing the global search characteristic and fast convergence speed. Promising experimental results are obtained in terms of accuracy and real-time response capability to alert operators automatically

Keywords

feature extraction; image sequences; learning (artificial intelligence); neural nets; parameter estimation; crowd estimation; feature indexes; global search; hybrid global learning; least-squares; neural-based; sequences of images; surveillance in complex scenes; underground station; Automatic control; Cameras; Convergence; Feature extraction; Head; Infrared detectors; Monitoring; Neural networks; Real time systems; Surveillance;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/3477.775269

Filename

775269