Automated Multi-Camera Surveillance: Algorithms and Practice [electronic resource] / by Omar Javed, Mubarak Shah.

Automated Video Surveillance -- Identifying Regions of Interest in Image Sequences -- Object Detection and Categorization -- Object Tracking in a Single Camera -- Tracking in Multiple Cameras with Disjoint Views -- Knight Surveillance System Deployment -- Concluding Remarks.

The deployment of surveillance systems has captured the interest of both the research and the industrial worlds in recent years. The aim of this effort is to increase security and safety in several application domains such as national security, home and bank safety, traffic monitoring and navigation, tourism, and military applications. The video surveillance systems currently in use share one feature: A human operator must monitor them at all times, thus limiting the number of cameras and the area under surveillance and increasing cost. A more advantageous system would have continuous active warning capabilities, able to alert security officials during or even before the happening of a crime. Existing automated surveillance systems can be classified into categories according to: The environment they are primarily designed to observe; The number of sensors that the automated surveillance system can handle; The mobility of sensor. The primary concern of this book is surveillance in an outdoor urban setting, where it is not possible for a single camera to observe the complete area of interest. Multiple cameras are required to observe such large environments. This book discusses and proposes techniques for development of an automated multi-camera surveillance system for outdoor environments, while identifying the important issues that a system needs to cope with in realistic surveillance scenarios. The goal of the research presented in this book is to build systems that can deal effectively with these realistic surveillance needs. .