Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reliable Quasi-Static Post-Fall Floor-Occupancy Detection Using Low-Cost Millimetre-Wave Radar

Huy Trinh, Phuong Thai, Elliot Creager, George Shaker

TL;DR

This paper tackles reliable post-fall floor occupancy detection in long-term care using a low-cost 60 GHz mmWave radar. It reframes the problem as a quasi-static sensing task and introduces a MVDR/Capon range-azimuth preprocessing pipeline, contrasted with a vendor DBF baseline, followed by CA-CFAR detection. The proposed method delivers higher mean frame-positive rates (≈0.92) and better reliability across viewpoints and locations, with zero false alarms on empty rooms in the reported data, highlighting improved robustness in cluttered indoor settings. The work advances privacy-preserving ambient monitoring for LTC environments and suggests future integration with fall response workflows and post-fall vital-sign monitoring.

Abstract

As the population ages rapidly, long-term care (LTC) facilities across North America face growing pressure to monitor residents safely while keeping staff workload manageable. Falls are among the most critical events to monitor due to their timely response requirement, yet frequent false alarms or uncertain detections can overwhelm caregivers and contribute to alarm fatigue. This motivates the design of reliable, whole end-to-end ambient monitoring systems from occupancy and activity awareness to fall and post-fall detection. In this paper, we focus on robust post-fall floor-occupancy detection using an off-the-shelf 60 GHz FMCW radar and evaluate its deployment in a realistic, furnished indoor environment representative of LTC facilities. Post-fall detection is challenging since motion is minimal, and reflections from the floor and surrounding objects can dominate the radar signal return. We compare a vendor-provided digital beamforming (DBF) pipeline against a proposed preprocessing approach based on Capon or minimum variance distortionless response (MVDR) beamforming. A cell-averaging constant false alarm rate (CA-CFAR) detector is applied and evaluated on the resulting range-azimuth maps across 7 participants. The proposed method improves the mean frame-positive rate from 0.823 (DBF) to 0.916 (Proposed).

Reliable Quasi-Static Post-Fall Floor-Occupancy Detection Using Low-Cost Millimetre-Wave Radar

TL;DR

This paper tackles reliable post-fall floor occupancy detection in long-term care using a low-cost 60 GHz mmWave radar. It reframes the problem as a quasi-static sensing task and introduces a MVDR/Capon range-azimuth preprocessing pipeline, contrasted with a vendor DBF baseline, followed by CA-CFAR detection. The proposed method delivers higher mean frame-positive rates (≈0.92) and better reliability across viewpoints and locations, with zero false alarms on empty rooms in the reported data, highlighting improved robustness in cluttered indoor settings. The work advances privacy-preserving ambient monitoring for LTC environments and suggests future integration with fall response workflows and post-fall vital-sign monitoring.

Abstract

As the population ages rapidly, long-term care (LTC) facilities across North America face growing pressure to monitor residents safely while keeping staff workload manageable. Falls are among the most critical events to monitor due to their timely response requirement, yet frequent false alarms or uncertain detections can overwhelm caregivers and contribute to alarm fatigue. This motivates the design of reliable, whole end-to-end ambient monitoring systems from occupancy and activity awareness to fall and post-fall detection. In this paper, we focus on robust post-fall floor-occupancy detection using an off-the-shelf 60 GHz FMCW radar and evaluate its deployment in a realistic, furnished indoor environment representative of LTC facilities. Post-fall detection is challenging since motion is minimal, and reflections from the floor and surrounding objects can dominate the radar signal return. We compare a vendor-provided digital beamforming (DBF) pipeline against a proposed preprocessing approach based on Capon or minimum variance distortionless response (MVDR) beamforming. A cell-averaging constant false alarm rate (CA-CFAR) detector is applied and evaluated on the resulting range-azimuth maps across 7 participants. The proposed method improves the mean frame-positive rate from 0.823 (DBF) to 0.916 (Proposed).
Paper Structure (9 sections, 14 equations, 9 figures, 2 tables)

This paper contains 9 sections, 14 equations, 9 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodologies
  3. Experiment Setup and Data Collection
  4. FMCW Radar Signal Processing
  5. Vendor Digital Beamforming (DBF) Baseline
  6. Proposed MVDR/Capon Range-Azimuth Processing
  7. Cell-Averaging Constant False Alarm Rate
  8. Results
  9. Conclusion

Figures (9)

  • Figure 1: Infineon XENSIV™ BGT60TR13C Radar. infineon2024bgt60tr13c
  • Figure 2: Experimental setup and viewpoints. Two wall-mounted radar viewpoints (TV-side and Window-side) are used to observe post-fall floor occupancy across five floor locations (P1--P5) under real room clutter and occlusions.
  • Figure 3: Few example post-fall floor postures from the dataset. Subjects lie on the floor in multiple quasi-static poses (a) supine with arms extended, (b) side-prone, and (c) supine with knees bent. Furniture is intentionally placed near the subject to create multipath and partial occlusions.
  • Figure 4: CA-CFAR sensitivity tuning on Subject 1's dataset. Macro-F1, frame-level false positive rate (FPR), and true positive rate (TPR) are shown as the CA-CFAR scale factor $k$ is swept. The selected operating points $k$ satisfy the FPR cap (0.1) while maximizing Macro-F1 for each method.
  • Figure 5: Qualitative comparison of DBF and our proposed detectors on frame 9 for subject 1 lying on the floor at position 1 (window view), which both of them produce detections within the ground-truth bounding box.
  • ...and 4 more figures