Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UbiHR: Resource-efficient Long-range Heart Rate Sensing on Ubiquitous Devices

Haoyu Bian, Bin Guo, Sicong Liu, Yasan Ding, Shanshan Gao, Zhiwen Yu

TL;DR

Key to UbiHR is a real-time long-range spatio-temporal model enabling noise-independent heart rate recognition and display on commodity mobile devices, along with a set of mechanisms for prompt and energy-efficient sampling and preprocessing.

Abstract

Ubiquitous on-device heart rate sensing is vital for high-stress individuals and chronic patients. Non-contact sensing, compared to contact-based tools, allows for natural user monitoring, potentially enabling more accurate and holistic data collection. However, in open and uncontrolled mobile environments, user movement and lighting introduce. Existing methods, such as curve-based or short-range deep learning recognition based on adjacent frames, strike the optimal balance between real-time performance and accuracy, especially under limited device resources. In this paper, we present UbiHR, a ubiquitous device-based heart rate sensing system. Key to UbiHR is a real-time long-range spatio-temporal model enabling noise-independent heart rate recognition and display on commodity mobile devices, along with a set of mechanisms for prompt and energy-efficient sampling and preprocessing. Diverse experiments and user studies involving four devices, four tasks, and 80 participants demonstrate UbiHR's superior performance, enhancing accuracy by up to 74.2\% and reducing latency by 51.2\%.

UbiHR: Resource-efficient Long-range Heart Rate Sensing on Ubiquitous Devices

TL;DR

Key to UbiHR is a real-time long-range spatio-temporal model enabling noise-independent heart rate recognition and display on commodity mobile devices, along with a set of mechanisms for prompt and energy-efficient sampling and preprocessing.

Abstract

Ubiquitous on-device heart rate sensing is vital for high-stress individuals and chronic patients. Non-contact sensing, compared to contact-based tools, allows for natural user monitoring, potentially enabling more accurate and holistic data collection. However, in open and uncontrolled mobile environments, user movement and lighting introduce. Existing methods, such as curve-based or short-range deep learning recognition based on adjacent frames, strike the optimal balance between real-time performance and accuracy, especially under limited device resources. In this paper, we present UbiHR, a ubiquitous device-based heart rate sensing system. Key to UbiHR is a real-time long-range spatio-temporal model enabling noise-independent heart rate recognition and display on commodity mobile devices, along with a set of mechanisms for prompt and energy-efficient sampling and preprocessing. Diverse experiments and user studies involving four devices, four tasks, and 80 participants demonstrate UbiHR's superior performance, enhancing accuracy by up to 74.2\% and reducing latency by 51.2\%.

Paper Structure

This paper contains 45 sections, 6 equations, 25 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. User study
  3. Survey Findings
  4. User Demands on Fast and Long-term Heart Rate Sensing
  5. Limitations of existing heart rate sensing tools.
  6. Willingness to use contactless and ubiquitous heart rate sensing tools
  7. Design Goals
  8. Why Camera-based Physiological Sensing
  9. SYSTEM DESIGN
  10. Overview
  11. Adaptive Duty-cycling Facial Video Sampling
  12. Dynamic Noise-aware Facial Image Pre-processing
  13. Fast Long-range Spatio-temporal Heart Rate Recognizing
  14. Primer on Long-range Spatio-temporal Model for HR Detection
  15. Incorporating Temporal Shift to 2D Convolution for Lightweight Spatio-temporal Modeling
  16. ...and 30 more sections

Figures (25)

  • Figure 1: Questionnaire survey on a hospital cardiology department and user experience of UbiHR.
  • Figure 2: Survey results: (a) What method(s) do you currently use to measure HR? (b) Do you feel uncomfortable with the HR measurement method(s) that require skin contact (such as wearing a chest strap or finger clip?) (c) Do you often forget to wear or use HR measurement devices that require skin contact? (d) What features would you like the tool to have? (e) Do you think there is a need for a contactless HR sensing tool in addition to your current HR measurement method(s)?
  • Figure 3: Illustration of the principle of mapping cardio-pulmonary and facial signal for contactless heart rate sensing.
  • Figure 4: Workflow of UbiHR system.
  • Figure 5: Illustration of the adaptive duty cycling facial video sensing mechanism (the mosaic is to protect privacy).
  • ...and 20 more figures