Small sample HRRP identification method and system based on wavelet scattering transformation

• Main Authors: CHEN BIN, HU DEXIU, YANG XINGYUAN, CHENG WEIYI, ZHANG HONGMIN, WEI SHANXIN, LI ZHIKAI, WANG JIANTAO, MOU YANCHENG
• Format: Patent
• Language: Chinese; English
• Published: 25.06.2024
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; ELECTRIC DIGITAL DATA PROCESSING; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; TESTING

The invention provides a small sample HRRP identification method and system based on wavelet scattering transformation. The method comprises the following steps: step 1, preprocessing a target HRRP; 2, wavelet scattering transformation is carried out on the preprocessed target HRRP, and a scattering characteristic matrix of the target HRRP is obtained; and step 3, inputting the scattering feature matrix into a trained neural network model to obtain a target recognition result. According to the invention, the wavelet scattering feature matrix of the HRRP is extracted through wavelet scattering transformation, and the feature matrix is used as the input of the neural network model, so that the target recognition precision under the condition of small samples can be improved. 本发明提供一种基于小波散射变换的小样本HRRP识别方法和系统。该方法包括：步骤1：对目标HRRP进行预处理；步骤2：对预处理后的所述目标HRRP进行小波散射变换，得到所述目标HRRP的散射特征矩阵；步骤3：将所述散射特征矩阵输入至训练好的神经网络模型，得到目标识别结果。本发明通过小波散射变换提取HRRP的小波散射特征矩阵，将该特征矩阵作为神经网络模型的输入，可以提高小样本情况下目标识别精度。