Details |
The new trend in military and peacekeeping operations is to use Unattended Ground Sensors (UGS), which use a variety of sensor technologies (including acoustic, seismic, magnetic, electric field, and imaging) to perform remote target detection, tracking, localization and recognition. UGS’s are used in a variety of areas including border surveillance, special force operations, airfield protection, perimeter and building protection, target acquisition, situational awareness, force protection, remote monitoring, and etc. UGS’s improve the ability of tactical units to collect information and are expected to play an increasingly important role in military operations. UGS’s are deployed in the battlefield randomly using different deployment methods (e.g., via aerial deployment) and their detected information is transmitted wirelessly back to monitoring command and control stations, providing real time intelligence data. The deployed sensors are self-organizing to form a multi-hop network. Because of power limitations, UGS’s are required to process data locally, and report only the results of this analysis. Reported data includes the classification, identification and tracking of objects entering the sensor field.
This research focuses on the application of estimation and data fusion techniques to the detection, classification, localization and tracking of targets with unattended ground sensors (UGS). Tracking of multiple targets in a UGS network requires the classification of targets using a set of features extracted from measured data. These features may be taken from different sensors with modalities and hence, a collaborative signal-processing algorithm is needed in order to enhance the target tracking accuracy by combining information from different sensors.
|