class="info-alert">『Your web browser does not support JavaScript, but it does not affect browsing through the rest of the web site.』
jump to main content

Industrial Technology Research Institute

:::

ITRI Uses AI Technology to Accurately Detect Body Temperature

Date:2020/04/09

Thermal Image Body Temperature Irregularity Detection Technology Defends the Public amid the COVID-19 Epidemic

As the Novel Coronavirus (COVID-19) pandemic continues its march throughout the globe, taking one's temperature has become one of a crucial steps in containing the spread of the virus. On April 9th, ITRI in its first ever online press conference unveiled its Thermal Image Body Temperature Irregularity Detection Technology, an R&D result supported by the Technology Development Programs of Department of Industrial Technology (DoIT), Ministry of Economic Affairs (MOEA). This technology relies on non-contact detection of infrared energy to determine body temperature and features four main characteristics, namely AI facial recognition, indoor/outdoor adaptability, dynamic measurement for multiple persons, and ability to deploy quickly. The technology has already been introduced in elementary and secondary schools in Taipei City and Penghu, serving as a first line of defense to protect public health and safety.

ITRI President Edwin Liu in the institute’s first ever online press conference remarked that amid the COVID-19 outbreak, ITRI is using its technological expertise to assist society. He mentioned that ITRI has participated in the government-organized National Mask Production Team, working closely with the industrial sector to expand output of locally made masks. This effort has been instrumental in enabling Taiwan to become the world's second largest manufacturer of masks, safeguarding the health of the public and putting citizens at greater ease. ITRI has also been releasing weekly reports to provide updates on the impact of the epidemic on industry, thus helping enterprises understand the latest state of the pandemic and enable them to respond as best as they can. The Thermal Image Body Temperature Irregularity Detection Technology announced today, he said, is able to rapidly detect fevers, making the technology especially useful in the body temperature measurement for a large crowd. Dr. Liu concluded that ITRI will continue to employ its cross-disciplinary strengths and announce even more R&D successes to fight the epidemic.

ITRI Executive Vice President Pei-Zen Chang pointed out that according to a report from the World Health Organization in February 2020, among the COVID-19 confirmed cases who have developed symptoms, 87.9% of them had fevers. Therefore, temperature screening serves as an important public health measure to catch possible COVID-19 infections at the first line and promptly isolate those with fevers. ITRI's technology offers a high level of accuracy thanks to the AI facial recognition that focuses on faces to measure head temperature. There is no worry that pets or passing vehicles will impact the image. The technology also alleviates concerns that people holding hot food or beverages will be mistakenly detected as having overly high temperatures. In addition, Dr. Chang stated that ITRI's smart temperature compensation technology reduces external environmental interference, such as light, airflow or humidity. This means that people can be screened outdoors. In contrast, most existing infrared body temperature sensors can only be used indoors. In conjunction with the Internet of Things (IoT), the technology can be linked to and controlled by a mobile phone, making it easy to use and alleviating the need for professionally trained individuals to operate it.

ITRI's Smart Microsystems Technology Center General Director Chun-Hsun Chu stated that ITRI's Thermal Image Body Temperature Irregularity Detection Technology combines a variety of innovative R&D results, including AI facial technology, which quickly captures facial images and carries out infrared body temperature sensing. Meanwhile, its constant temperature control technology minimizes indoor and outdoor temperature differences. A color image correcting algorithm can simulate high-quality sensing, and IoT is employed in linking personal mobile phones to other information-related machinery. This fever detection technology is applicable for use at the entrances to places where large numbers of people file through, such as schools, housing communities, corporate security posts, and public mass transport. The technology has been conducting field verification since March, with cooperation between the Ministry of Economic Affairs and the Taipei City Department of Education leading to its roll-out at Bihu Elementary School and Zhonglun Senior High School. In April, the technology will be used on a broader scale, with cooperation with the Penghu County Education Department leading to temperature measurement at schools there. In the future, the technology will be deployed throughout Taiwan and cooperation will be initiated with domestic manufacturers to engage in production on a larger scale, which will lead to the broader industrial applications.

ITRI unveiled its Thermal Image Body Temperature Irregularity Detection Technology in an online press conference on April 9, 2020.
ITRI unveiled its Thermal Image Body Temperature Irregularity Detection Technology in an online press conference on April 9, 2020.
The technology can distinguish one’s head temperature from the heat of food or beverages and can be used outdoors.
The technology can distinguish one’s head temperature from the heat of food or beverages and can be used outdoors.