ADAS/AD

This paper proposes a novel Recursive Convolutional Target Detector (RCTD) for Frequency-Modulated Continuous-Wave (FMCW) radar in complex automotive scenarios. Leveraging a lightweight convolutional neural network, RCTD efficiently localizes multiple targets despite strong interference. Detailed simulations and a hardware prototype on an FPGA-based deep learning processor demonstrate real-time feasibility, low false alarm rates, and higher detection accuracy under stringent resource constraints.