Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/75893
Título: | AI based monitoring of different risk levels in COVID-19 context |
Autor(es): | Melo, César Dixe, Sandra Manuela Gonçalves Fonseca, Jaime C. Moreira, António H. J. Borges, João |
Palavras-chave: | COVID-19 Deep learning Supervised learning Object detection Keypoint detection |
Data: | 2022 |
Editora: | Multidisciplinary Digital Publishing Institute (MDPI) |
Revista: | Sensors |
Citação: | Melo, C.; Dixe, S.; Fonseca, J.C.; Moreira, A.H.J.; Borges, J. AI Based Monitoring of Different Risk Levels in COVID-19 Context. Sensors 2022, 22, 298. https://doi.org/10.3390/s22010298 |
Resumo(s): | COVID-19 was responsible for devastating social, economic, and political effects all over the world. Although the health authorities imposed restrictions provided relief and assisted with trying to return society to normal life, it is imperative to monitor people’s behavior and risk factors to keep virus transmission levels as low as possible. This article focuses on the application of deep learning algorithms to detect the presence of masks on people in public spaces (using RGB cameras), as well as the detection of the caruncle in the human eye area to make an accurate measurement of body temperature (using thermal cameras). For this task, synthetic data generation techniques were used to create hybrid datasets from public ones to train state-of-the-art algorithms, such as YOLOv5 object detector and a keypoint detector based on Resnet-50. For RGB mask detection, YOLOv5 achieved an average precision of 82.4%. For thermal masks, glasses, and caruncle detection, YOLOv5 and keypoint detector achieved an average precision of 96.65% and 78.7%, respectively. Moreover, RGB and thermal datasets were made publicly available. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/75893 |
DOI: | 10.3390/s22010298 |
ISSN: | 1424-8220 |
Versão da editora: | https://www.mdpi.com/1424-8220/22/1/298 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
sensors-22-00298-v2.pdf | 4,74 MB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons