Non-Contact Bed-Based Monitoring of Vital Signs

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.


Bennett, Stephanie Louise




Vital signs are a set of commonly measured signals used internationally as a baseline in medicine and surgery and are one of the most accurate predictors of clinical and physiological deterioration. Despite the clear clinical importance of vital sign measurements, there is often missed or inadequate documentation of patient vital sign measurements. The development of unobtrusive, automated and continuous monitoring offers the potential to enhance the safety and quality of patient care.

This thesis details a system that uses multiple modalities to capture data and data processing techniques to extract vital signal measurements and vital signal measurement abnormalities related to subject morbidities. This thesis focuses on the examination, testing and improvement upon a current visible light video processing technique intended to extract vital signal measurements, and expand it's use to thermal infrared video vital signal extraction.

Three modalities were used to gather data from healthy adult subjects and older adult in-hospital patients: thermal infrared cameras, visible light cameras and pressure sensitive mats. Subjects participated in several experimental procedures including video data capture of faces, hands and feet as well as in-bed pressure mat data capture. This data was subjected to several stages of data processing to extract vital signal measurements, which include pulse, respiration temperature and mobility measurements. Data segmentation using binary masks, level set method, and watershed method were used to identify regions of interest. An adaptive spatio-temporal video processing algorithm, the main thesis contribution, was used to extract vital signal measurements. The developed algorithm was assessed for its performance in vital signal estimation, as well its robustness with respect to noise. The whole system was assessed for its ability to extract vital signal measurements, and vital signal measurement abnormalities associated with possible subject morbidities.

The whole system demonstrated accurate vital signal measurement extraction, and the ability to detect signal abnormalities associated with subject morbidities. The developed algorithm was able to improve upon previous versions. Furthermore, several patterns associated with system failure were identified. This work demonstrated the potential for multiple sensor systems in conjunction with data processing to improve current methods of extracting vital signal data.


Engineering - Biomedical
Computer Science
Engineering - Electronics and Electrical




Carleton University

Thesis Degree Name: 

Doctor of Philosophy: 

Thesis Degree Level: 


Thesis Degree Discipline: 

Engineering, Electrical and Computer

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).