Datasets & Competitions
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.
- Categories:
27 Views
We have designed a ZYNQ SDR-based platform that utilizes real on-air 5G new radio (NR) signals to develop and test the performance of channel estimation for wireless channel estimators. On-air samples are obtained via the SDR platform to determine the unknown values of the channel response using known values at the pilot locations. We have collected extensive channel estimation data under a variety of scenarios: 1) line-of-sight (LOS), 2) LOS multipath and 3) non-LOS multipath. We have considered 2m,4m,6m test cases to simulate meter-level indoor positioning for indoor scenarios.
- Categories:
842 Views