FKEE - Official Portal

FACULTY OF ELECTRICAL &
ELECTRONICS ENGINEERING

Abstract:

Viral outbreaks such as SARS, H5N1, and H1N1 have led the need of temperature monitoring in areas where crowds are expected such as in hospitals and airports. Infrared (IR) thermal screening, hitherto, has been found as powerful, quick and non-invasive method to detect the elevated temperature of febrile individuals when the temperature of the face is above 36°. Past research has proved that the most excellent area that represents the core body temperature is the medial canthal areas of the face as it is less dependent on the effects of ambient temperature. In realistic situation, the moving subjects are random and the angles of the skin surface and distances change dynamically and misdetection of canthal area could also be due to any other unwanted objects that have the same temperature. The normal approach is to ask a single person to stand still for 2 seconds to capture the temperature. However this approach is ineffective and this will lead to long queue in public. To solve this issue, we have proposed a combination of physiology-based and optical flow algorithm to extract vascular network from the face. The thermal camera is provided with colour and audible alarming, hence when the camera detect an abnormal temperature from a person, automatic febrile individual tracking alarm will report to the operator the current location of the individual.