Guardado en:
Detalles Bibliográficos
Autores principales: Tanaka, Tomoya, Ikeda, Tomonori, Yonemoto, Ryo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.13018
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917146753236992
author Tanaka, Tomoya
Ikeda, Tomonori
Yonemoto, Ryo
author_facet Tanaka, Tomoya
Ikeda, Tomonori
Yonemoto, Ryo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comprehensive Deployment-Oriented Assessment for Cross-Environment Generalization in Deep Learning-Based mmWave Radar Sensing
Tanaka, Tomoya
Ikeda, Tomonori
Yonemoto, Ryo
Computer Vision and Pattern Recognition
Machine Learning
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.
title Comprehensive Deployment-Oriented Assessment for Cross-Environment Generalization in Deep Learning-Based mmWave Radar Sensing
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2512.13018