328 / 2020-01-06 13:52:00

Memory-Based Neural Network for Radar HRRP Noncooperative Target Recognition

In this paper, we propose a Memory-Based Discriminative module(MMBD) for Radar Automatic Target Recognition (RATR) based on High Resolution Range Profile (HRRP) in imbalanced case to learn how to find out the discriminative representations and generalize the ability to barely appeared target samples of some categories. Specifically, we utilize CNN to explore discriminative features among HRRP samples and employ the memory module to record misclassified samples or samples that are correctly classified with low confidence into a external storage, we called it buffer. Then we leverage a Bi-LSTM to merge the classified samples with the most similar ones in the buffer to make the final decision. It is worth noting that MMBD can be inserted as a plug-and-play module into any discriminative methods. Effectiveness and efficiency are evaluated on the measured data.