Towards Radar Emitter Recognition in Changing Environments with Domain Generalization
This addresses the practical challenge of inconsistent radar signal distributions for electronic warfare systems, though it appears to be an incremental improvement over existing domain generalization methods.
The paper tackles the problem of radar emitter recognition in changing electronic warfare environments where signal distributions vary, proposing a domain generalization framework that achieves superior performance in comparative experiments.
Analyzing radar signals from complex Electronic Warfare (EW) environment is a non-trivial task.However, in the real world, the changing EW environment results in inconsistent signal distribution, such as the pulse repetition interval (PRI) mismatch between different detected scenes.In this paper, we propose a novel domain generalization framework to improve the adaptability of signal recognition in changing environments.Specifically, we first design several noise generators to simulate varied scenes. Different from conventional augmentation methods, our introduced generators carefully enhance the diversity of the detected signals and meanwhile maintain the semantic features of the signals. Moreover, we propose a signal scene domain classifier that works in the manner of adversarial learning. The proposed classifier guarantees the signal predictor to generalize to different scenes. Extensive comparative experiments prove the proposed method's superiority.