A SYSTEM FOR COUNTING PEOPLE IN VIDEO IMAGES USING NEURAL NETWORKS TOIDENTIFY THE BACKGROUND SCENE

A method for counting the number of people in any pre-defined scene is described. The method has three distinct stages: image pre-processing , background identification and object search. The method was designed to provide accurate counts, even when the background scene was allowe d to vary. This tolerance to changes in the background scene was achie ved using RAM-based neural network classifiers to identify sections of the background scene in each test image. The system was implemented o n relatively low cost hardware and was found to give good results at m oderately high frame rates. Copyright (C) 1996 Pattern Recognition Soc iety. Published by Elsevier Science Ltd.