Adaptive-Frequency Resonate-and-Fire Neurons for Spectral Estimation of Streaming Radar Signals
This work addresses memory and latency bottlenecks in radar signal processing for resource-constrained edge applications by introducing a neuromorphic approach that eliminates the need for large data buffers.
The paper proposes a neuromorphic-inspired method using adaptive resonate-and-fire neurons for spectral estimation of FMCW radar signals, enabling sample-by-sample processing with memory scaling with the number of targets rather than signal length, and demonstrates successful multi-target tracking on simulated and experimental data.
Frequency Modulated Continuous Wave (FMCW) radar systems traditionally rely on Fourier-based methods, such as the Fast Fourier Transform (FFT), to estimate target range and velocity. While computationally efficient, these approaches require storing and processing large blocks of data, which can become a bottleneck in memory-constrained or low-latency applications. In this work, we propose a neuromorphic-inspired signal processing method based on adaptive resonate-and-fire (ARF) neurons formulated as a discrete-time dynamical system. Each neuron dynamically adjusts its internal frequency to match dominant frequency components of the input radar signal, enabling direct estimation of target ranges and velocities without computing the full frequency spectrum. The proposed model operates in a sample-by-sample fashion, resulting in memory requirements that scale with the number of tracked targets rather than the signal length. A feedback mechanism is also introduced to enable multiple neurons to lock on distinct frequency components in multi-target cases. Results on simulated and experimental data demonstrate that the method can successfully track multiple targets. Compared to conventional FFT-based approaches, the proposed method offers reduced memory usage proportional only to the number of tracked targets, making it suitable for resource-constrained and edge-based radar applications.