Multi-radar Identity and Ranging for Occupational Safety
MIRO is a privacy-preserving system that combines continuous PM sensing with a multi-radar mmWave re-identification framework, where distributed PM sensors measure local pollution levels and overlapping radars track and re-associate workers across views without using cameras; a GAN-based view adaptation model corrects azimuth-related distortions in range-Doppler signatures to maintain identity consistency, and experiments show 90.4% re-ID F1-score and 0.70 SSIM, with field tests in stone-cutting yards confirming reliable worker-specific exposure estimation.
Key Features
Uniqueness: . MIRO is 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.
- Azimuth-Aware View Adaptation: A Pix2Pix-based network that translates range-Doppler signatures across radar viewpoints using motion signatures.
- Cross-Radar Identity Persistence: A spatio-temporal correlation based association that maintains consistent identity across multiple radar nodes.
- Real-World Deployment: Tested across different industrial workspaces for estimmation of workers' activity specific pollution estimation .
Licensing:The platform source and the collected dataset is free to download and can be used with GNU Affero General Public License for non-commercial purposes. All participants signed forms consenting to the collected mmwave dataset and activity labels for non-commercial research purposes. The institute’s ethical review committee has approved the field study (Order No: IIT/SRIC/DEAN/2023, Dated July 31, 2023).
Contributors
Tirthankar Halder
IIT Kharagpur, India
Argha Sen
IIT Kharagpur, India
Swadhin Pradhan
Cisco Systems, US
Rijurekha Sen
IIT Delhi, India
Sandip Chakraborty
IIT Kharagpur, India
Teaser Video
Publications
- Tirthankar Halder, Argha Sen, Swadhin Pradhan, Rijurekha Sen, and Sandip Chakraborty. "MIRO: Multi-radar Identity and Ranging for Occupational Safety.", ACM/IEEE SenSys 2026