Track-Before-Detect for Multiframe Detection With Censored Observations

In this work, we address the problem of target detection from multiple noisy observations produced by a generic sensor. A two-step approach is considered, wherein a censoring stage retains the significant measurements (i.e., those whose likelihood ratio exceeds a primary threshold) in each frame, while a multiframe detector elaborates the preprocessed observations and takes the final decision through a generalized likelihood ratio test. A dynamic programming algorithm to form the decision statistic, which exploits the sparse nature of the censored observations, is proposed. A closed-form complexity analysis is provided, and a thorough performance assessment is undertaken to elicit the tradeoffs among censoring level, system complexity, and achievable performance.