基于CNN的雷达航迹分类方法

Radar Track Classification Method Based on CNN

针对雷达目标识别问题,提出了一种航迹级的目标分类方法,基于目标航迹的运动学特征,应用卷积神经网络对目标航迹数据进行训练和分类。应用对数处理方法对数据进行预处理,搭建基于残差网络(ResNet)的深度学习模型,再应用连续识别策略,对目标类型进行综合判定。实验结果表明该方法可有效实现雷达目标航迹的分类识别。

Aiming at the radar target recognition problem,a track level target classification method is proposed.Based on the kinematic characteristics of target track,convolution neural network is used to train and classify the target track data.Logarithmic processing method is applied to preprocess the data,and deep learning model based on residual network(ResNet)is built,then continuous identification strategies are applied to make comprehensive judgment of target types in this paper.Experimental results show that this method can effectively realize the classification and recognition of radar target track.