Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on Hardware
Detecting vital signs by using a contactless camera-based approach can provide several advantages over traditional clinical methods, such as lower financial costs, reduced visit times, increased comfort, and enhanced safety for healthcare professionals. Specifically, Eulerian Video Magnification (EV...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/9/4550 |
| _version_ | 1827742589492658176 |
|---|---|
| author | Dimitrios Kolosov Vasilios Kelefouras Pandelis Kourtessis Iosif Mporas |
| author_facet | Dimitrios Kolosov Vasilios Kelefouras Pandelis Kourtessis Iosif Mporas |
| author_sort | Dimitrios Kolosov |
| collection | DOAJ |
| description | Detecting vital signs by using a contactless camera-based approach can provide several advantages over traditional clinical methods, such as lower financial costs, reduced visit times, increased comfort, and enhanced safety for healthcare professionals. Specifically, Eulerian Video Magnification (EVM) or Remote Photoplethysmography (rPPG) methods can be utilised to remotely estimate heart rate and respiratory rate biomarkers. In this paper two contactless camera-based health monitoring architectures are developed using EVM and rPPG, respectively; to this end, two different CNNs, (Mediapipe’s BlazeFace and FaceMesh) are used to extract suitable regions of interest from incoming video frames. These two methods are implemented and deployed on four off-the-shelf edge devices as well as on a PC and evaluated in terms of latency (in each stage of the application’s pipeline), throughput (FPS), power consumption (Watt), efficiency (throughput/Watt), and value (throughput/cost). This work provides important insights about the computational costs and bottlenecks of each method on each hardware platform, as well as which platform to use depending on the target metric. One of our insights shows that the Jetson Xavier NX platform is the best platform in terms of throughput and efficiency, while Raspberry Pi 4 8 GB is the best platform in terms of value. |
| first_indexed | 2024-03-11T04:06:13Z |
| format | Article |
| id | doaj.art-c49a72a346b846c6b65dd942236c058a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:06:13Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c49a72a346b846c6b65dd942236c058a2023-11-17T23:46:00ZengMDPI AGSensors1424-82202023-05-01239455010.3390/s23094550Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on HardwareDimitrios Kolosov0Vasilios Kelefouras1Pandelis Kourtessis2Iosif Mporas3School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UKSchool of Engineering, Computing and Mathematics, University of Plymouth, Plymouth PL4 8AA, UKSchool of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UKSchool of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UKDetecting vital signs by using a contactless camera-based approach can provide several advantages over traditional clinical methods, such as lower financial costs, reduced visit times, increased comfort, and enhanced safety for healthcare professionals. Specifically, Eulerian Video Magnification (EVM) or Remote Photoplethysmography (rPPG) methods can be utilised to remotely estimate heart rate and respiratory rate biomarkers. In this paper two contactless camera-based health monitoring architectures are developed using EVM and rPPG, respectively; to this end, two different CNNs, (Mediapipe’s BlazeFace and FaceMesh) are used to extract suitable regions of interest from incoming video frames. These two methods are implemented and deployed on four off-the-shelf edge devices as well as on a PC and evaluated in terms of latency (in each stage of the application’s pipeline), throughput (FPS), power consumption (Watt), efficiency (throughput/Watt), and value (throughput/cost). This work provides important insights about the computational costs and bottlenecks of each method on each hardware platform, as well as which platform to use depending on the target metric. One of our insights shows that the Jetson Xavier NX platform is the best platform in terms of throughput and efficiency, while Raspberry Pi 4 8 GB is the best platform in terms of value.https://www.mdpi.com/1424-8220/23/9/4550embedded systemsAI/ML health monitoring algorithmsefficient health monitoring hardware platformsreal-time health monitoring |
| spellingShingle | Dimitrios Kolosov Vasilios Kelefouras Pandelis Kourtessis Iosif Mporas Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on Hardware Sensors embedded systems AI/ML health monitoring algorithms efficient health monitoring hardware platforms real-time health monitoring |
| title | Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on Hardware |
| title_full | Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on Hardware |
| title_fullStr | Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on Hardware |
| title_full_unstemmed | Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on Hardware |
| title_short | Contactless Camera-Based Heart Rate and Respiratory Rate Monitoring Using AI on Hardware |
| title_sort | contactless camera based heart rate and respiratory rate monitoring using ai on hardware |
| topic | embedded systems AI/ML health monitoring algorithms efficient health monitoring hardware platforms real-time health monitoring |
| url | https://www.mdpi.com/1424-8220/23/9/4550 |
| work_keys_str_mv | AT dimitrioskolosov contactlesscamerabasedheartrateandrespiratoryratemonitoringusingaionhardware AT vasilioskelefouras contactlesscamerabasedheartrateandrespiratoryratemonitoringusingaionhardware AT pandeliskourtessis contactlesscamerabasedheartrateandrespiratoryratemonitoringusingaionhardware AT iosifmporas contactlesscamerabasedheartrateandrespiratoryratemonitoringusingaionhardware |