DEKF system for crowding estimation by a multiple-modelapproach

3 March 1994

journal article
Published by Institution of Engineering and Technology (IET) in Electronics Letters

Vol. 30 (5) , 390-391
https://doi.org/10.1049/el:19940280

Abstract

A distributed extended Kalman filter (DEKF) network devoted to real-time crowding estimation for surveillance in complex scenes is presented. Estimation is carried out by extracting a set of significant features from sequences of images. Feature values are associated by virtual sensors with the estimated number of people using nonlinear models obtained in an off-line training phase. Different models are used, depending on the positions and dimensions of the crowded subareas detected in each image.

Keywords

DISTRIBUTED EXTENDED KALMAN FILTER
COMPLEX SCENES
VIRTUAL SENSORS
CROWDED SUBAREAS
FEATURE VALUES
SIGNIFICANT FEATURES
IMAGE SEQUENCES
MULTIPLE-MODEL APPROACH
DEKF SYSTEM
SURVEILLANCE
NONLINEAR MODELS
REAL-TIME CROWDING ESTIMATION
OFF-LINE TRAINING PHASE

This publication has 0 references indexed in Scilit: