Abstract
Synthetic aperture radar (SAR) often receives interference from multiple emitters operating within the same frequency band. These interference signals are densely overlapped in time and frequency domains and strongly coupled with SAR echoes, which substantially increases the difficulty of signal recognition and sorting. In conventional processing chains, recognition and sorting are treated as independent modules with task-specific inputs, resulting in severe information fragmentation and cumulative-error propagation under dense interference conditions. To address these limitations, this paper proposes a unified recognition-sorting network for overlapping SAR interference signals, termed Uni-RSNet. Based on continuous multi-frame time-frequency representations, Uni-RSNet jointly captures high-dimensional intra-pulse features and inter-pulse temporal correlations of signals from the same emitter, enabling simultaneous modulation classification, pulse-parameter estimation, and emitter attribution. This framework extends interference recognition from isolated pulses to entire frames, while simultaneously imposing modulation-aware constraints on the signal sorting process. Furthermore, a statistically consistent contrastive objective is designed to enhance intra-emitter compactness and inter-emitter separability, while a geometric consistency constraint improves the robustness of pulse localization. The unified architecture compresses the conventional serial processing chain and eliminates the need for task-dependent input adjustments. Extensive experiments on both simulated and GaoFen-3 (GF-3) satellite data demonstrate the superior performance of the proposed method under dense interference conditions. The code and datasets are publicly available at: https://github.com/QianyueXue/Uni-RSNet.
Funding Information
  • National Natural Science Foundation of China (62131019)

This publication has 59 references indexed in Scilit: