Radar Modulation Recognition of Intra-pulse Overlapping Signals

Existing work on radar modulation recognition iswidely based on the assumption of a single in-pulse signal,whereas overlapping two pulse signals is an actual situation. Thispaper introduces a challenging problem: modulation recognitionof overlapping intra-pulse signals, where the difficulty lies inthe fact that the number of samples grows stepwise with thepermutation of the sub-signals. In this paper, for the first time,a series of methods for target detection are used to solve thisproblem well. Specifically, the authors construct a time-frequencydataset of overlapping signals and train the model’s abilityto extract TFmeta on a single signal.

现有关于雷达调制识别的研究普遍基于单脉冲信号的假设，然而双脉冲信号的叠加却是实际存在的情况。本文提出了一项颇具挑战性的问题：重叠脉冲信号的调制识别，其难点在于样本数量随子信号的排列而逐步增加。在本文中，作者首次运用一系列目标检测方法有效解决了这一问题。具体而言，作者构建了一个重叠信号的时频数据集，并训练模型在单个信号上提取TF元信息的能力。