| Project Id
|
BITSRMIT024B001315
|
| Project Detail
|
| Project Title
|
Non-contact physiological monitoring from facial videos
|
| Senior Supervision Team (BITS)
|
| Supervisor name and Title
|
Amalin Prince A
|
School or Department (or company, if applicable)
|
BITS PILANI, GOA CAMPUS
|
|
|
|
Email ID
|
amalinprince@goa.bits-pilani.ac.in
|
| URL for more info
|
https://www.bits-pilani.ac.in/goa/amalin-prince-a/
|
| a) Are you currently supervising a BITS or RMIT HDR student?
|
YES
|
| Please comment how many you are supervising
|
5
|
| b) Have you supervised an offshore candidate before?
|
NO
|
| If no, what support structures do you have in place?
|
|
| If yes, please elaborate
|
N
|
| Senior Supervision Team (RMIT)
|
| Supervisor name and Title
|
Shaun Cloherty
|
School or Department (or company, if applicable)
|
STEM
|
|
|
|
Email ID
|
shaun.cloherty@rmit.edu.au
|
| URL for more info
|
https://www.rmit.edu.au/contact/staff-contacts/academic-staff/c/cloherty-dr-shaun
|
| a) Are you currently supervising a BITS or RMIT HDR student?
|
YES
|
| Please comment how many you are supervising
|
2
|
| b) Have you supervised an offshore candidate before?
|
NO
|
| If no, what support structures do you have in place?
|
|
| If yes, please elaborate
|
N
|
| Other Supervisors (BITS)
|
| Supervisor name and Title
|
|
School or Department (or company, if applicable)
|
|
| Phone Number (Optional)
|
|
Email ID
|
|
| URL for more info
|
|
| Other Supervisors (BITS)
|
| Supervisor name and Title
|
Dr Priya Rani
|
School or Department (or company, if applicable)
|
STEM
|
| Phone Number (Optional)
|
+61410784111
|
Email ID
|
priya.rani@rmit.edu.au
|
| URL for more info
|
https://www.rmit.edu.au/contact/staff-contacts/academic-staff/r/rani-dr-priya
|
| Field of Research (For Codes)
|
| 400399 | Biomedical engineering not elsewhere classified | 20.00 |
| 460299 | Artificial intelligence | 40.00 |
| 460304 | Computer Vision | 40.00 |
|
| Project Description
|
|
The gold standard for measuring cardiovascular parameters is the electrocardiogram (ECG). The ECG measures small changes in electrical potential at the surface of the body caused by contraction of the heart. ECG can provide a rich picture of cardiac health and disease. However, measuring the ECG requires specialised skill and equipment, and is typically not compatible with medical imaging modalities such as magnetic resonance imaging (MRI). There is a need for reliable non-invasive techniques for physiological monitoring to aid faster and comfortable diagnosis of cardiovascular health. Remote photo-plethysmography (rPPG) is an alternative technique for estimating heart rate from facial videos by measuring changes in reflected light intensity caused by changes in blood flow in the skin. The accuracy of rPPG is typically limited by the confounding effects of skin colour and interference due to changes in illumination. A related technique, image ballistocardiography (iBCG), also uses facial video to estimate heart rate but uses micro-vibrations of facial features caused by propagating pressure waves in the blood vessels. This technique is more robust to skin pigmentation and changes in illumination, but is susceptible to noise due to the rigid and non-rigid motion of the subject. Combining rPPG and iBCG derived from facial video has the potential to produce robust physiological estimates with accuracy exceeding either technique alone. This project therefore aims to investigate estimation of heart rate and a rich set of physiological parameters from simultaneous rPPG and iBCG signals extracted from facial videos. This work has the potential to enable low-cost, non-contact, physiological monitoring of cardiovascular health in the home or clinics.
|
| Project Deliverable/Outcomes
|
|
The expected outcomes are: 1. A novel dataset containing facial videos and simultaneous ECG and PPG recordings. 2. Novel algorithms and artifical intelligence/machine learning models for physiological monitoring from facial videos, and 3. Demonstrated applicability of the above algorithms and models for real-time non-contact physiological monitoring.
|
| Research Impact Themes
|
| BETTER HEALTH OUTCOMES | AFFORDABLE HEALTH AND PREVENTABLE DISEASES |
| ADVANCED DIGITAL TECHNOLOGIES AND BUSINESS TRANSFORMATION | DEEP LEARNING AND PREDICTIVE MODELLING |
| BETTER HEALTH OUTCOMES | HEALTH INNOVATION AND BIOMEDICAL AND WEARABLE DEVICES |
|
| Which RMIT Sustainable Development Goal (SDG) does your project align to
|
|
GOOD HEALTH AND WELLBEING
|
| Which RMIT Enabling Impact Platform (EIP) does your project align to
|
|
BIOMEDICAL AND HEALTH INNOVATION
|
| Which RMIT Program code will this project sit under?
|
|
DR239 (BIOMEDICAL)
|
| Student Capabilities and Qualifications
|
|
Programming (e.g., Python or Matlab), Signal processing.
|
|
Image processing, Computer vision, Biomedical signals, Machine learning
|
|
MSc, MTech, BTech/BE
|
| Preferred discipline of Student
|
| Artificial Intelligence, Deep Learning, Information Extraction & Knowledge Extraction, Machine Learning, Natural Language Processing |
| Computer Vision, Image Processing, Virtual Reality |
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Data Science |
|