基于时频图像处理的JEM分类识别方法

Jem Based Extraction and Classification Method On Time-freauery Image Processing

机载雷达探测飞机目标时,可通过提取JEM特征进行直升飞机、螺旋桨飞机、喷气式飞机分类识别,虽然其理论基础已相对成熟,但在机载杂波背景下对低SNR调制信号的检测与分类识别有待进一步提升,以改进工程化过程中分类识别的稳健性。文中在回顾JEM理论分析的基础上,分析了观测角度、叶片螺距、转子交调、RCS闪烁、雷达工作波形等因素对JEM回波的影响,提出了基于超分辨时频图像的融合检测方法,综合预处理、时频分析、时频图像融合检测、JEM特征判决等策略,解决杂波背景下低SNR调制回波的检测与识别难题,并用机载雷达实测民航飞机的回波数据进行了验证,具备较高的工程应用价值。

Airborne radar can classify helicopter,propeller-driven aircraft and jet aircraft by using Jet Engine Modulation(JEM)characteristic when it detects flying machines.Although the theory is relatively mature,the detection and classification method of JEM with low signal-to-noise ratio(SNR)in the background of airborne clutter can be improved in search of greater robustness in engineering process.The effect in radar echoes with JEM of Observation Angle,Leaf Blade Pitch,Cross Modulation of Rotors,Radar Cross-Secion(RCS)scintillation,Radar Waveform is analyzed on the basis of the related theories.A method of fusion detection based on time-frequency images with super resolution is proposed.The mixed strategy of pre-processing,time-frequency analysis,fusion detection based on time-frequency images,JEM classification is used to for detection and classification of JEM signal with low SNR in clutter background.The method is validated with real radar data.The results show that this new method has import project application values.