Evaluation of SAR Deception Jamming Effect based on Convolutional Neural Network

Deceptive jamming (DJ) is an effective means to jam Synthetic aperture radar (SAR) at present. DJ effect is an important indicator to measure the performance of DJ against SAR. This paper analyzes the evaluation accuracy of existing DJ evaluation indicators, and then propose a new evaluation method of DJ online based on convolutional neural network (CNN). The proposed method avoids the second introduction of errors when calculating jamming indicators. Meanwhile, this paper takes the influence of SAR track measuring error on DJ as an example to generate DJ images. Finally, the moving and stationary target acquisition and recognition(MSTAR) data set is used as the DJ template to verify the effectiveness of the method.