Self-organizing cooperative sensor network for remote surveillance: improved target tracking results
Richard A. Burne, Ivan Kadar, John C. Whitson, Anna L. Buczak · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2001
The current trend to develop low cost, miniature unattended ground sensors will enable a cost-effective, covert means for surveillance in both urban and remote border areas. Whereas the functionality (e.g., sensing range and life in the field) of these smaller UGS (i.e., acoustic, seismic, magnetic, chemical or biological) may be limited due to size and cost constraints, a network of these sensors working cooperatively together can provide an effective surveillance capability. A key factor is the ability of these sensors to work cooperatively to achieve a `collective' functionality that can meet the surveillance objective. This paper describes results of using target identification (ID) features (i.e., the ID feature space of the target) to improve the tracking of closely spaced targets (i.e., the kinematic space of the targets). A Multiple Level Identification (MLID) approach was used to determine and maintain confidences for multiple target identifications for each target. These confidences were incorporated into the processing of kinematic data (i.e., target bearing reports) to improve the tracker's estimated position of the target's location. Results describing the effectiveness of using MLID on target tracking performance are reported using simulated target trajectory and ID data.