With the swift advancement of radar jamming techniques, the variety of active jamming types and the diversity of jamming strategies have surged, urging for accurate identification of jamming types. Conventional active jamming identification methods lack efficiency and universality. Meanwhile, current deep learning-based approaches are encumbered by large-scale parameters and the need for extensive data, which significantly limit their practical applications. To enhance recognition capabilities under conditions with limited parameters and data, a lightweight few-shot radar active jamming identification method based on multi-modality fusion is proposed. Lightweight fusion is achieved by leveraging the temporal locality of time-frequency features and the high-resolution range profile features. Additionally, few-shot classification performance is improved through exploiting metric learning and feature retrieval techniques. Experiments conducted on both simulated and measured datasets demonstrate the superior performance of the proposed method under a variety of conditions.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |