Low altitude, small radar cross-section (RCS), and slow speed (LSS) targets, for example small unmanned aerial vehicles (UAVs), have become increasingly significant. In this paper, we propose a new automatic target recognition (ATR) system and a complete ATR chain based on multi-dimensional features and multi-layer classifier system using L-band holographic staring radar. We consider all steps of the processing required to make a classification decision out of the raw radar data, mainly including preprocessing for the raw measured Doppler data including regularization and main frequency alignment, selection, and extraction of effective features in three dimensions of RCS, micro-Doppler, and motion, and multi-layer classifier system design. We design creatively a multi-layer classifier system based on directed acyclic graph. Helicopters, small fixed-wing, and rotary-wing UAVs, as well as birds are considered for classification, and the measured data collected by L-band radar demonstrates the effectiveness of the proposed complete ATR classification system. The results show that the ATR classification system based on multi-dimensional features and k-nearest neighbors (KNN) classifier is the best, compared with support vector machine (SVM) and back propagation (BP) neural networks, providing the capability of correct classification with a probability of around 97.62%.

In this paper, a computationally efficient long-time integration and parameters estimation method via Keystone transform(KT), Radon Transform(RT) and Lv’s Transform(LVT) is proposed. Firstly, the KT-Radon is used to eliminate the range cell migration(RCM) of the echo after pulse compression, then using LVT to obtain the long-time integration and parameters estimation of high-speed target with acceleration motion. Compared with the GRFT algorithm, the proposed method only needs one dimensional search for range. Compared with the KT-FRFT algorithm, there is no need to search Doppler fold factor in this proposed method. So the proposed method doesn’t suffer from huge computation cost and obtain a good tradeoff between the computational cost and detection performance in comparison with the above algorithms. Finally, several experiments are provided to demonstrate the effectiveness of RadonKT -LVT.