Tracking and classification using aspect-dependent RCS and kinematic data

Abstract

The joint target tracking and classification using target-to-sensor aspect-dependent Radar Cross Section (RCS) and kinematic data for multistatic sonar network is presented in this paper. The scattered signals measured from different orientations of a target may vary due to aspect-dependant RCS. A complex target may contain several dozen significant scattering centers and dozens of other less significant scatterers. Because of this multiplicity of scatterers, the net RCS pattern exhibits high variation with aspect angle. Thus, radar cross sections from multiple aspects of a target, which are obtained via multiple sensors, will help in accurately determining the target class. By modeling the deterministic relationship that exits between RCS and target aspect, both the target class information and the target orientation can be estimated. Kinematic data are also very helpful in determining the target class as it describes the target motion pattern and its orientation. The proposed algorithm exploits the inter-dependency of target state and the target class using aspect-dependent RCS and kinematic information in order to improve both the state estimates and classification of each target. The simulation studies demonstrate the merits of the proposed joint target tracking and classification algorithm based on aspect-dependant RCS and kinematic information.

Joint class identification and target classification using multiple HMMs

“…In addition, in the joint target tracking and classification algorithm [12][13][14] and its variant the simultaneous tracking and classification algorithm [15], kinematic and real feature measurements are jointly exploited for a better classification. Such approach has also been considered in [16] as well. Furthermore, in [17] a related approach is proposed in the framework of belief functions: Several alternative frames (sets of possible classes) are built, and the most appropriate frame is the one that minimizes a joint entropy-conflict criterion.…”

Two-level automatic multiple target joint tracking and classification

“…In recent works, it is suggested that performance improvement can be expected in both tracker and classifier by taking advantage of exchanging information with each other [1][2][3]. Target classification information supplied by the classifier can be used to improve tracking accuracy [4], data association performance and tracking purity and continuity [5]. Also, the target state estimated by tracker can be sent to the classifier as the input when attribute measurement is unavailable.…”

“…The existing tracking and classification algorithms can be broadly categorized into two classes. The algorithms presented in [1,3,4] rely on both kinematic measurement and attribute measurement such as images, signal intensity and so forth. In algorithms proposed in [6], only the kinematic measurement is assumed to be available, because measuring the target's attribute is infeasible in some surveillance applications due to sensing distance, weather conditions or device limitation.…”