Fast Event Detection in Mission-Critical Surveillance with Wireless Video Sensor Networks

Wireless Video Sensor Network (WVSN) can be used for efficient event detection such as intrusion detection or disaster relief systems. These applications have a high level of criticality and can not be deployed with the current state of technology. In this paper, we show how a dynamic criticality management scheme can provide fast event detection for mission-critical surveillance applications. Based on a criticality model that uses modified Bezier curves to determine for each sensor node the corresponding frame capture rate, simulation results show that the network lifetime can be increased, that the stealth time is kept low and that sentry nodes succeed in detecting intrusions.