An Autonomous Approach to Deinterleave and Recover Radar Pulse Sequences in an Unknown Maritime Environment

In a high-density maritime environment, the recovery of radar pulse sequences presents a challenge for transponders due to interleaved pulses. Furthermore, because only a few manufacturers produce civil radars, the lack of diversity in signal signatures makes the task more difficult. In this paper, we introduce a new approach to deinterleave radar pulse sequences without requiring specific knowledge. Our proposed solution, based on a three-step approach, enables transponders to recognize their environment and interact with emitters more effectively without any training step. The effectiveness of this approach is demonstrated through simulations. The obtained results show that predicted clusters have a homogeneity score higher than 98%, a completeness score higher than 92%, and a Rand index higher than 97%. Our solution can deinterleave and recover radar pulse sequences in an unknown maritime environment in real-time without prior knowledge, while providing a thorough interpretation of results