Comprehensive Deployment-Oriented Assessment for Cross-Environment Generalization in Deep Learning-Based mmWave Radar Sensing
It addresses the practical deployment challenge of maintaining robust accuracy in radar sensing under spatial variations, with incremental improvements over existing methods.
This study tackled the problem of cross-environment generalization for deep learning-based mmWave radar sensing in people counting, finding that sigmoid-based amplitude weighting reduced RMSE by 50.1% and MAE by 55.2%, while transfer learning achieved up to 91.3% MAE reduction for large spatial shifts.
This study presents the first comprehensive evaluation of spatial generalization techniques, which are essential for the practical deployment of deep learning-based radio-frequency (RF) sensing. Focusing on people counting in indoor environments using frequency-modulated continuous-wave (FMCW) multiple-input multiple-output (MIMO) radar, we systematically investigate a broad set of approaches, including amplitude-based statistical preprocessing (sigmoid weighting and threshold zeroing), frequency-domain filtering, autoencoder-based background suppression, data augmentation strategies, and transfer learning. Experimental results collected across two environments with different layouts demonstrate that sigmoid-based amplitude weighting consistently achieves superior cross-environment performance, yielding 50.1% and 55.2% reductions in root-mean-square error (RMSE) and mean absolute error (MAE), respectively, compared with baseline methods. Data augmentation provides additional though modest benefits, with improvements up to 8.8% in MAE. By contrast, transfer learning proves indispensable for large spatial shifts, achieving 82.1% and 91.3% reductions in RMSE and MAE, respectively, with 540 target-domain samples. Taken together, these findings establish a highly practical direction for developing radar sensing systems capable of maintaining robust accuracy under spatial variations by integrating deep learning models with amplitude-based preprocessing and efficient transfer learning.