Neural Modeling Fields for Multitarget/Multisensor Tracking

We describe a new approach for combining range and Doppler data from multiple radar platforms to perform multi-target detection and tracking. In particular, we assume azimuthal measurements are either coarse or unavailable, so that multiple sensors are required to triangulate target tracks using range and Doppler measurements only. The algorithm framework is based upon neural modeling fields, a biologically-inspired neural architecture, which yields advantages over conventional multi-target tracking algorithms by reducing the computational complexity during data association by several orders of magnitude. The algorithm is tested on synthetic multi-sensor data, and the results demonstrate that accurate tracks can be estimated by exploiting spatial diversity in the sensor locations. These results are promising, and demonstrate a surprising degree of robustness in the presence of nonhomogeneous clutter and uncertainty in the number of targets.