Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MIRO: Multi-radar Identity and Ranging for Occupational Safety

Tirthankar Halder, Argha Sen, Swadhin Pradhan, Rijurekha Sen, Sandip Chakraborty

Abstract

Occupational exposure to airborne particulate matter (PM) poses a severe health risk in open industrial workspaces such as stonecutting yards. Conventional monitoring solutions such as wearable PM sensors and camera-based tracking are impractical due to discomfort, maintenance issues, and privacy concerns. We present MIRO, a privacy-preserving framework that integrates continuous PM sensing with a multi-radar millimeter-wave (mmWave) re-identification (re-ID) backbone. A distributed network of PM sensors captures localized pollutant concentrations, while spatially overlapping mmWave radars track and re-associate workers across viewpoints without relying on visual cues. To ensure identity consistency across radars, we introduce a GAN-based view adaptation network that compensates for azimuthal distortions in range-Doppler (RD) signatures, combined with correlation-based cross-radar matching. In controlled laboratory experiments, our system achieves a re-ID F1-score of 90.4% and a mean Structural Similarity Index Measure (SSIM) of 0.70 for view adaptation accuracy. Field trials in rural stone-cutting yards further validate the system's robustness, demonstrating reliable worker-specific PM exposure estimation.

MIRO: Multi-radar Identity and Ranging for Occupational Safety

Abstract

Occupational exposure to airborne particulate matter (PM) poses a severe health risk in open industrial workspaces such as stonecutting yards. Conventional monitoring solutions such as wearable PM sensors and camera-based tracking are impractical due to discomfort, maintenance issues, and privacy concerns. We present MIRO, a privacy-preserving framework that integrates continuous PM sensing with a multi-radar millimeter-wave (mmWave) re-identification (re-ID) backbone. A distributed network of PM sensors captures localized pollutant concentrations, while spatially overlapping mmWave radars track and re-associate workers across viewpoints without relying on visual cues. To ensure identity consistency across radars, we introduce a GAN-based view adaptation network that compensates for azimuthal distortions in range-Doppler (RD) signatures, combined with correlation-based cross-radar matching. In controlled laboratory experiments, our system achieves a re-ID F1-score of 90.4% and a mean Structural Similarity Index Measure (SSIM) of 0.70 for view adaptation accuracy. Field trials in rural stone-cutting yards further validate the system's robustness, demonstrating reliable worker-specific PM exposure estimation.
Paper Structure (49 sections, 10 equations, 15 figures, 2 tables)

This paper contains 49 sections, 10 equations, 15 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Closing the Multi-Radar re-ID Gap
  3. Real-World Validation in Harsh Settings
  4. Contributions
  5. Related Work
  6. Occupational Exposure Monitoring
  7. Activity and Worker Behavior Monitoring
  8. mmWave and RF-Based Human Sensing
  9. Multi-Sensor Cross-View Re-Identification
  10. Background and Pilot Study
  11. Preliminaries: mmWave Radar Sensing
  12. Range estimation
  13. Velocity estimation
  14. Point cloud estimation
  15. Survey of Stone-Cutting Workers
  16. ...and 34 more sections

Figures (15)

  • Figure 1: MIRO's multi-mmwave radar re-identification (re-ID) in action. It resolves cross-view identity ambiguity due to overlapping regions, where each radar assigns distinct local user IDs (e.g., $U_{11}$, $U_{21}$) to the same worker ($P_1$), by performing activity-correlated re-ID, while co-located PM sensors enable personalized exposure estimation.
  • Figure 2: Illustration of azimuthal dependence of range-Doppler (RD) signatures. In stone-work, most motions (body/tool) occur within the azimuthal-plane, producing variations in azimuth angles ($A_i$). Elevation-plane motions ($E_i$) contribute less, yielding nearly identical RD responses.
  • Figure 3: Survey results from stone-cutting workers.
  • Figure 4: Detailed experimental setup.
  • Figure 5: PM exposure analysis.
  • ...and 10 more figures