This work aims at demonstrating the usefulness of exploiting novel image-pr
ocessing tools for moving-object detection and classification in the contex
t of an actual application involving the remote monitoring of a tourist sit
e. The application concerns outdoor people counting for tourist-how estimat
ion in a constrained environment. The technical problems to be solved are c
oncerned with: (a) the design and implementation of low-complexity backgrou
nd updating and change detection algorithms able to adapt themselves to the
time-varying illumination scene conditions, and (b) the integration of rea
l-time pattern-recognition tools in order to distinguish group of persons t
o be counted from other objects present in the scene. The achieved results
have proven that the proposed system makes it possible to obtain reliable p
eople counting in different environmental situations, with an absolute mean
error at most equal to 10%. (C) 2001 Elsevier Science B.V. All rights rese
rved.