College of Science, University of Diyala discussed a master dissertation on automated approach to thermal video screening based on stereo vision for tracking COVID-19 cases by the postgraduate student, Mr. Ahmed Abdul Sattar Karim.
The dissertation aimed at contributing to the development of an effective and accurate system for detecting human body temperature using machine learning techniques, with the growing need for remote and automated temperature checking in various environments such as airports, hospitals and public places.
The dissertation proposed two models, the first using calibration methods for color and thermal videos with the K-means algorithm, while the second used Deep Semantic Segmentation, pre-trained on the data extracted from the first model.
The dissertation demonstrated that the second pre-trained model showed better and higher results in all scales used.
Contact us for any inquiries about the services provided by the Ministry of Higher Education and Scientific Research
