In pandemic conditions such as COVID-19, the measurement of vital signs such as body temperature and heart rate becomes the basis for conducting health screenings. To reduce physical contact and potential hazards, this measurement process can be carried out non-contact. The non-contact measurements carried out in this study used a thermal imaging approach. To reduce the potential danger of transmission, this non-contact measurement device is applied to a security robot. The non-contact measurement method using thermal imaging is done by processing a thermal image on the forehead area. Changes in temperature in the forehead area are then entered into a bandpass filter with a frequency of 0.75 Hz to 3 Hz, which is the frequency range of the human heartbeat under normal circumstances. Calculating heart rate is carried out with two approaches, namely peak to peak interval and fast Fourier transform. Based on the peak-to-peak interval approach, the accuracy is 89.24%, with a standard deviation of 5.6. Meanwhile, with the dominant frequency detection approach using the fast Fourier transform, the accuracy value is slightly better, at 91.84%, with a standard deviation of 4.81.
Copyrights © 2022