Multimodal target detection via integrated GLRT

The focus of this paper is the multimodal detection and localization of a ground moving target based on radio frequency (RF) and infrared (IR) data. The target radiates a low probability of intercept (LPI) RF signal received by multiple passive RF sensors at scene and is imaged by using a stationary IR camera concurrently. To obtain the multimodal detector proposed in this paper, first, the generalized likelihood ratio test (GLRT) is employed to derive the RF and IR detectors individually. Then, the RF and IR detectors are integrated optimally to get the integrated GLRT. In order to avoid the computational complexity associated with the integrated GLRT, a suboptimal multimodal detector is implemented by applying the random basis functions (RBF) approach to the IR image sequence to reduce down the search space for the RF detector. It is shown that the suboptimal multimodal detector has better localization performance compared to the RF detector when one of the RF sensors is partially occluded.