Dual Attention Network for Heart Rate and Respiratory Rate Estimation

  title={Dual Attention Network for Heart Rate and Respiratory Rate Estimation},
  author={Yuzhuo Ren and Braeden Syrnyk and Niranjan Avadhanam},
  journal={2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)},
Heart rate and respiratory rate measurement is a vital step for diagnosing many diseases. Non-contact camera based physiological measurement is more accessible and convenient in Telehealth nowadays than contact instruments such as fingertip oximeters since non-contact methods reduce risk of infection. However, remote physiological signal measurement is challenging due to environment illumination variations, head motion, facial expression, etc. It’s also desirable to have a unified network which… 

Figures and Tables from this paper


DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks
This work proposes the first end-to-end system for video-based measurement of heart and breathing rate using a deep convolutional network, which significantly outperforms all current state-of-the-art methods on both RGB and infrared video datasets.
RhythmNet: End-to-End Heart Rate Estimation From Face via Spatial-Temporal Representation
This paper proposes an end-to-end RhythmNet for remote HR estimation from the face using RyhthmNet, a spatial-temporal representation encoding the HR signals from multiple ROI volumes as its input and feeds into a convolutional network for HR estimation.
Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement
Comprehensive experiments are performed to show that the proposed method not only achieves superior performance on compressed videos with high-quality videos pair, but also generalizes well on novel data with only compressed videos available, which implies the promising potential for real-world applications.
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
This work presents a video-based and on-device optical cardiopulmonary vital sign measurement approach that leverages a novel multi-task temporal shift convolutional attention network (MTTS-CAN) and enables real-time cardiovascular and respiratory measurements on mobile platforms.
Video-based respiration monitoring with automatic region of interest detection
A video-based respiration monitoring method that automatically detects a respiratory region of interest (RoI) and signal using a camera and seems to provide a valid solution to ECG in confined motion scenarios, though precision may be reduced for neonates.
Camera-based system for contactless monitoring of respiration
A camera-based monitoring system to reliably measure respiration rate without any body contact is proposed and a computationally efficient algorithm to extract raw breathing signals from the video stream has been developed and implemented.
Remote PPG based vital sign measurement using adaptive facial regions
A remote photoplethysmography measurement technique where human skin color variations are analysed for observing human vital signs including but not limited to average heart rate and variation, which offers a novel signal processing approach.
Effects of Video Encoding on Camera-Based Heart Rate Estimation
It is shown that increasing the compression rate decreases the accuracy of heart rate estimation, but that resolution can be reduced (up to a cutoff point) and color subsampling can be applied for reducing file size without a big impact onheart rate estimation.
Robust heart rate from fitness videos
The results suggest that the proposed SB method considerably increases the robustness of heart-rate measurement in challenging fitness applications, and outperforms the state-of-the-art method.
Detecting Pulse from Head Motions in Video
This method tracks features on the head and performs principal component analysis (PCA) to decompose their trajectories into a set of component motions and chooses the component that best corresponds to heartbeats based on its temporal frequency spectrum.