Joint Sparsity Based Heterogeneous Data-Level Fusion for Multi-Target Discovery

Most traditional surveillance systems use decisionor feature-level fusion approaches to integrate heterogeneous sensor data, which are sub-optimal with information loss. In this paper, we continue our previous work on joint-sparse data-level fusion (JSDLF) to integrate heterogeneous sensor data. Since heterogeneous sensor data originate from the same targets of interest, whose states can be determined by only a few parameters, it is reasonable to assume that the sensor measurement domain has a low intrinsic dimensionality. The proposed JSDLF approach is based on the joint sparse signal recovery techniques by discretizing the target state space. The JSDLF approach can fuse signals from multiple distributed passive radio frequency (RF) sensors and video sensor data for joint target detection, state estimation, and high level information fusion situation awareness. The JSDLF approach is data-driven and requires minimum prior information, since there is no need to know the time-varying RF signal amplitudes, or the image intensity of the targets. It can handle non-linearity in the sensor data due to state space discretization and the use of frequency/pixel selection matrices to reduce user involvement. In our previous work, the JSDLF approach was developed for a single-target case. In this paper, we extend the JSDLF approach to detect and estimate multiple targets. For a multi-target case with J targets, the JSDLF approach only requires discretization in a single-target state space, instead of discretization in a J-target state space, as in the case of the generalized likelihood ratio test (GLRT) or the maximum likelihood estimator (MLE). Numerical examples are provided to demonstrate that the proposed JSDLF approach achieves excellent performance with accurate target position and velocity estimates to support situation awareness.