Researchers from the University of South Australia have developed an AI-based computer vision system that can help doctors automatically detect a premature baby’s face and skin and remotely monitor their vital signs while in intensive care.
The University of South Australia is working on a study published in the Journal of Imaging that will replace contact-based electrical sensors with non-contact video cameras to avoid skin tearing and potential infections. This would be especially beneficial for babies whose delicate skin could tear from the adhesive pads applied by the electrodes, which can also lead to infection.

Researchers remotely monitored seven infants’ heart and respiratory rates in a neonatal intensive care unit at Flinders Medical Centre using cameras. Using the dataset of videos of babies in NICU, a ‘baby detector’ was developed to detect their skin tone and faces reliably.
Infants were filmed with high-resolution cameras at close range to capture subtle color changes from heartbeats and body movements not visible to the human eye. Non-contact vital sign readings that matched an ECG and outperformed conventional electrodes have endorsed the value of non-contact monitoring in intensive care for preterm babies.
The research team claims that recording clear videos of premature babies in the NICU setting is incredibly challenging. There are many obstructions, and lighting can also vary, so getting accurate results can be difficult. However, their Non-contact detection model performed beyond expectations.
On average, 10% of babies are born prematurely worldwide. The main reason for this is their vulnerability to outside stimuli and the need to monitor vital signs continuously. Traditionally, these measurements have been done with adhesive electrodes placed on a baby’s skin, but it is believed that non-contact monitoring will be more efficient in the future.
The UniSA team developed world-first technology in 2020 that measures adults’ vital signs to screen for symptoms of COVID-19. This was later sold by North American company Draganfly and is now used in commercial products.
Paper: https://www.mdpi.com/2313-433X/7/8/122
Source: https://www.sciencedaily.com/releases/2021/08/210825113641.htm
Asif Razzaq is the CEO of Marktechpost Media Inc.. As a visionary entrepreneur and engineer, Asif is committed to harnessing the potential of Artificial Intelligence for social good. His most recent endeavor is the launch of an Artificial Intelligence Media Platform, Marktechpost, which stands out for its in-depth coverage of machine learning and deep learning news that is both technically sound and easily understandable by a wide audience. The platform boasts of over 2 million monthly views, illustrating its popularity among audiences.