Identification and Classification of Human Body Parts for Contactless Screening Systems: An Edge-AI Approach

Continuous monitoring of vital signs like body temperature and cardio-pulmonary rates can be critical in the early prediction and diagnosis of illnesses. Optical-based methods, i.e., RGB cameras and thermal imaging systems, have been used with relative success for performing contactless vital signs monitoring, which is of great value for pandemic scenarios, such as COVID-19. However, to increase the performance of such systems, the precise identification and classification of the human body parts under screening can help to increase accuracy, based on the prior identification of the Regions of Interest (RoIs) of the human body. Recently, in the field of Artificial Intelligence, Machine Learning and Deep Learning techniques have also gained popularity due to the power of Convolutional Neural Networks (CNNs) for object recognition and classification. The main focus of this work is to detect human body parts, in a specific position that is lying on a bed, through RGB and Thermal images. The proposed methodology focuses on the identification and classification of human body parts (head, torso, and arms) from both RGB and Thermal images using a CNN based on an open-source implementation. The method uses a supervised learning model that can run in edge devices, e.g. Raspberry Pi 4, and results have shown that, under normal operating conditions, an accuracy in the detection of the head of 98.97% (98.4% confidence) was achieved for RGB images and 96.70% (95.18% confidence) for thermal images. Moreover, the overall performance of the thermal model was lower when compared with the RGB model. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Contactless Smart Screening in Nursing Homes: An IoT-enabled solution for the COVID-19 era

In the COVID-19 era, the provision of health indicators seamlessly and without contact, in groups at risk such as the elderly, is crucial due to the fast spread of the disease and the need to act quickly to contain its evolution. Continuous monitoring of vital signs, such as body temperature and cardio-respiratory rates, can be vital in early detection and prediction of COVID-19, which rapidly progresses and particularly affects the elderly population in nursing homes. Conventional clinical methods used for monitoring vital signs are contact-based, require contact sensors that need to be precisely attached by a trained health professional, are less convenient for repeatable measurements, and not practical for long-term monitoring. On the other hand, contactless vital signs monitoring using radar-based techniques, or IR-thermal imaging, do not require the attachment of physical electrodes and can be of great value in health screening of patients and help health professionals in early detection of the COVID-19 in the elderly population, in the specific context of nursing houses. This work describes the design and specification of a low-cost contactless health screening system for nursing homes, and includes the design of an IoT Edge device that can be placed above the beds where patients rest, allowing the continuous acquisition of health information and its processing without any type of contact and invasiveness. © 2021 IEEE.

Evaluation of a Low-Cost COTS Bio Radar for Vital Signs Monitoring

With the beginning of the COVID-19 pandemic, there was a need for the Health Care Workers (HCW) to pay more attention to the vital signs of their patients. One way for this to happen, while respecting the social distance, is using contactless technologies, e.g. the bio radar. This way, the HCW will be able to monitor the respiration and heart rates of the patient, without getting close to him. For this to be possible, the best radar configurations were studied, as well as other important aspects that should be taken into consideration while monitoring a patient, for the results obtained to be reliable. © 2021 IEEE.