Target Recognition Through Time-Domain Scattering Echo based on CNN

In this paper, based on the shooting and bouncing ray (SBR) method to obtain a large number of target time-do main scattering echo data, an electrically large-size target echo dataset is produced, and two kinds of tank targets are recognized by using the convolutional neural network (CNN) model. The results show that compared with the target recognition using optical images, the target recognition by timedomain electromagnetic scattering data is better, and the minimum recognition accuracy of CNN for similar targets is above 95%.