Radar Modulation Recognition of Intra-pulse Overlapping Signals

Existing work on radar modulation recognition is

widely based on the assumption of a single in-pulse signal,

whereas overlapping two pulse signals is an actual situation. This

paper introduces a challenging problem: modulation recognition

of overlapping intra-pulse signals, where the difficulty lies in

the fact that the number of samples grows stepwise with the

permutation of the sub-signals. In this paper, for the first time,

a series of methods for target detection are used to solve this

problem well. Specifically, the authors construct a time-frequency

dataset of overlapping signals and train the model’s ability

to extract TFmeta on a single signal.