Activity Monitoring for ICU Patients Using Deep Learning and Image Processing

A patient in coma condition needs intense monitoring and care, but nowadays shortage of intensivist and critical care nurses is the major problem faced by the hospitals. Traditional method of monitoring ICU patients requires dedicated proactive observer to look at the patient all day long. One of the issues with traditional methods is that the observer has to be available all 24 h of the day and one observer will be able to monitor only one patient at a time. This paper aims to develop a system which overcomes these issues faced by traditional methods. The proposed system uses image processing and deep learning approach, with which the system can monitor the patients in critical care unit and can report to the doctor or nurse. The proposed system is capable of detecting target object (patient) in real time, further detect patient’s activity if any and notify the doctor or nurse. © 2020, Springer Nature Singapore Pte Ltd.