Abstract:
We present a proof-of-concept light detection and ranging (LiDAR) signal processing architecture that integrates a machine-learning-enhanced processing unit (PU) with on-chip time-to-digital converters (TDCs) to reduce bandwidth and memory requirements in SPAD-based direct time-of-flight (dToF) systems. The proposed architecture fits a Gaussian mixture model (GMM) to photon arrival time distributions …