Remote Breathing Monitoring Using LiDAR Technology

TL;DR

Problem: remote, non-contact, privacy-preserving breathing monitoring in real-world settings. Approach: a LiDAR-based pipeline that converts torso-point-cloud data into breathing signals via ROI filtering, centroid-based time series, moving-average smoothing, and peak/threshold detection, with respiratory rate $R$ defined as $R=\frac{\text{card}(\bar{\mathcal{B}})}{\tau}\times 60$. Contributions: validation across five postures shows robust detection of inhalation/exhalation, breath depth, breath-hold events, and breathing rate, with front views yielding the best performance; breath-depth RMSE is small and breath-hold detection is reliable via moving variance. Significance: enables privacy-preserving, remote, continuous respiratory monitoring across daily environments and clinical settings, resilient to ambient lighting and subject orientation.

Abstract

Breathing monitoring is crucial in healthcare for early detection of health issues, but traditional methods face challenges like invasiveness, privacy concerns, and limited applicability in daily settings. This paper introduces light detection and ranging (LiDAR) sensors as a remote, privacy-respecting alternative for monitoring breathing metrics, including inhalation/exhalation patterns, respiratory rates, breath depth, and detecting breathlessness. We highlight LiDARs ability to function across various postures, presenting empirical evidence of its accuracy and reliability. Our findings position LiDAR as an innovative solution in breathing monitoring, offering significant advantages over conventional methods.

Figures (6)

• Figure 1: The proposed system scenario and experimental setup.
• Figure 2: Illustration of the processed collected data.
• Figure 3: Human torso point cloud after filtering the raw data.
• Figure 4: Illustration of smoothing the noisy data.
• Figure 5: Illustration of the conducted experimentation.