Chapter 1: A Review of the State-of-the-Art in Distributed Surveillance Systems

1.1 Introduction

Intelligent visual surveillance systems deal with the real-time monitoring of persistent and transient objects within a specific environment. The primary aims of these systems are to provide an automatic interpretation of scenes and to understand and predict the actions and interactions of the observed objects based on the information acquired by sensors. The main stages of processing in an intelligent visual surveillance system are moving object detection and recognition, tracking, behavioural analysis and retrieval. These stages involve the topics of machine vision, pattern analysis, artificial intelligence and data management.

The recent interest for surveillance in public, military and commercial scenarios is increasing the need to create and deploy intelligent or automated visual surveillance systems. In scenarios such as public transport, these systems can help monitor and store situations of interest involving the public, viewed both as individuals and as crowds. Current research in these automated visual surveillance systems tends to combine multiple disciplines such as those mentioned earlier with signal processing, telecommunications, management and socio-ethical studies. Nevertheless there tends to be a lack of contributions from the field of system engineering to the research.

The growing research interest in this field is exemplified by the IEEE and IEE workshops and conferences on visual surveillance [ ^{[1] [2] [3] [4] [5] [6]}] and special issues that focus solely on visual surveillance in journals like [ ^{[7] [8] [9]}] or in human motion analysis like in [ ^[10]]. This chapter surveys the...