Real-Time Intrusion Detection and Tracking in Indoor Environment through Distributed RSSI Processing

Abstract

In the context of wireless sensor networks, the received signal strength indicator has been traditionally exploited for localization, distance estimation, and link quality assessment. Recent research has shown that, in indoor environments where nodes have been deployed, variations of the signal strength can be exploited to detect movements of persons. Moreover, the time histories of the received signal strength indicator of multiple links allow reconstructing the paths followed by the persons inside the monitored area. This approach, though effective, requires the transmission of multiple, raw received signal strength indicator time histories to a central sink node for off-line analysis. This consistently increases the latency and power consumption of the system. This work aims at applying distributed processing of the received signal strength indicator for indoor surveillance purposes. Through distributed processing, the nodes are able to autonomously detect and localize moving per-sons. The latency and power consumption of the system are minimized by transmitting to the sink node only the alerts related to significant events. Moreover, power consumption is further reduced through a high accuracy time synchronization protocol, which allows the nodes to keep the radio off for 60% of the time. During the tests, the system was able to detect the intrusion of a person walking inside the monitored area and to correctly track his movements in real-time with a 0.22 m average error. Possible applications of this application include surveillance of critical areas in buildings, enhancement of workers safety in factories, support to emergency workers or police forces in locating people e.g. during fires, hostage situations or terrorist attacks.