Non-Contact Bed-Based Monitoring of Vital Signs

Abstract

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 inhospital 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

Assemblages of forest conservation in Tanzania: gradients between chiefs, snakes, spirits and witches

“…People use this to say that there is some sort of witchcraft, because if he says those words and they happen, then how did he do that?" Chairperson, Namwanga, age 50-59. which do not sit well with underpinning rationalities of development, the non-rational agencies of animals and trees, of spirits and witches which, through their capacities to 'call a response' from humans 137 , have a legitimate place in an assemblage which has preserved local forests. Yet these agents are defined also by their relations to others, by gradients between material, political, social and immaterial forces 138 .…”

Automated vs. manual pain coding and heart rate estimations based on videos of older adults with and without dementia

“…Heart rate estimations from video data using the VM algorithm were analyzed as follows: 1) determined the start time and end time of the video segment to be analyzed; 2) selected a region of interest from an uncovered area of the skin (i.e., ensured that the area should be steady throughout the segment); 3) determined the window length for each processing cycle (2 to 6 seconds); 4) determined the overlap factor on the window processing cycles (10 to 90%) (i.e., a higher overlap percentage improves the resolution but increases the processing time); 5) determined the frequency ranges to be processed; and 6) determined the color component to be processed (green, red or blue). 73,79 We determined that green provided the most reliable estimate followed by red. Moreover, in line with our systematic approach, we chose a longer window for each processing cycle for better frequency resolution.…”

“…Given that our focus is to investigate FaceReader’s™ heart rate and pain expression estimations in relation to manual coding by experts, we selected video segments and skin regions with no movement to estimate the heart rate. The VM algorithm used in this study 58 , 73 , 74 has been verified through a comparison with wearable devices such as photoplethysmography (PPG). In the current study, in order to improve the reliability, the VM algorithm was applied to different areas of the body such as the face and hands.…”

“…As a result, our adaptive approach began with a wide frequency range to obtain a noisy estimate of the heart rate, then repeated the test with a narrower frequency range around the noisy estimate. 73 , 79 Based on the heart rate estimates calculated frame-by-frame by FaceReader™ and the VM algorithm, two heart rate estimates were produced for each participant: a mean heart rate value (i.e., calculated by summing the heart estimates [bpm] of each frame divided by the total number of frames per segment) for the no-pain and pain segments. We omitted a total of 17 (1.74%) frames from the FaceReader™ calculation, where FaceReader™ was not able to estimate a heart rate value because of the nature of the filming (e.g., patient movement).…”

Heart Rate Detection using Video Magnification: Impact of Algorithmic Parameters and Noise

“…In addition to these review articles, the PhD thesis documents for two students from Carleton university provide reviews of the literature generally focused on the EVM methodology using both RGB and thermal video techniques respectively [22], [23]. There has also been work in the literature that applies fusion-based methods of different cameras to estimate vital signs from facial video.…”