Non-ellipsoidal extended targets tracking from image observations based on ECK-MB-sub-random matrices filter

Joint detection and tracking of multiple extended objects from image observations is a challenging radar technology; especially for small back-scattering objects such as extended stealth targets (ESTs). This work provides a new approach for the ESTs tracking under the non-linear Gaussian system based on track-before-detect (TBD) approach. The sequential Monte Carlo multi-Bernoulli (SMC-MB) filter provides a good framework to cope with TBD approach. However, the SMC-MB filter suffers from the particles’ degradation problem seriously; especially for ETs tracking. Recently, the Cubature Kalman MB (CK-MB) filter which employs a third-degree spherical-radical cubature rule has been proposed to handle the nonlinear models, the CK-MB filter is more accurate and more principled in mathematical terms compared to SMC-MB filter. To this point, we address a TBD of ESTs with extended CK (ECK)-MB filter based on random matrices model (RMM), which is an efficient way to track ellipsoidal ESTs. In RMM-ESTs scenarios, although the extension ellipsoid is efficient, it may not be accurate enough because of lacking useful information, such as size, shape and orientation. Therefore, we introduce a filter composed of sub-ellipses; each one is represented by a RMM. The results confirm the effectiveness and robustness of the proposed ECK-Sub-RMM-MB-TBD filter.