Physics-Bounded mmWave Sensing for Schedulable, Privacy-Preserving Human Pose Estimation

2026-08-14

AI Summary

This study addresses the lack of deterministic execution and accuracy guarantees in edge-based millimeter-wave pose estimation by proposing PRISM. Leveraging the spatial concentration of RF reflections, this framework integrates physical constraints, adaptive instance proposal, and deadline-aware configuration to enable privacy-preserving, schedulable low-latency inference. Experimental results demonstrate that PRISM achieves superior pose estimation accuracy among feasible configurations while reducing 99th-percentile latency by 24%–58% and maintaining a 0% deadline miss rate. Consequently, this work effectively resolves the critical trade-off between real-time performance and estimation precision in edge computing environments, providing a robust solution for deterministic mmWave sensing applications.

Abstract

Millimeter-wave (mmWave) is a promising modality for human pose estimation (HPE) in mobile deployments with strong privacy requirements and limited resources, such as fall detection in bathrooms or activity monitoring in bedrooms, where cameras are inadmissible and computationally demanding processing is infeasible. Although mmWave signals naturally confine human reflections to compact, physically bounded regions, the algorithmic foundations of existing systems fail to provide deterministic execution and accuracy guarantees. They either process the full spectrum uniformly, resulting in unpredictable latency that varies across different scenes, or apply lossy compression that discards vital pose structures. To address this, we present PRISM, a framework that exploits the spatial concentration of RF reflections to achieve schedulable edge HPE. PRISM introduces three core components: 1) Physics-Bounded Integral Processing (PBIP), which restricts computation via constant-time integral queries; 2) Physics-Adaptive Instance Proposal (PAIP), which decomposes scenes involving multiple people into bounded local subproblems; and 3) Deadline-Aware Operation Profiles (DAOP), which provide offline-verified worst-case bounds for runtime quality-latency trade-offs. We evaluate PRISM on four public datasets spanning diverse radar configurations, reporting physical-bound and pose-accuracy measurements across this suite and examining deadline-aware scheduling on multi-person recordings together with an additional single-person set. Under single-threaded isolated execution, PRISM reduces 99th-percentile latency by 24\%--58\% relative to baselines that miss the deadline, records a 0.0\% miss rate on the evaluated traces, and attains the highest pose accuracy among deadline-feasible configurations, providing a practical route toward schedulable mmWave sensing on mobile edge hardware.

Problem

• mmWave sensing
• human pose estimation
• schedulability
• deterministic execution
• edge computing

Innovation

• Physics-Bounded Integral Processing
• Physics-Adaptive Instance Proposal
• Deadline-Aware Operation Profiles
• Schedulable Edge HPE
• mmWave Sensing