Beijing, April 9, 2020 – Megvii’s AI-enabled temperature screening solution has been deployed at 191 supermarkets across Beijing, including well-known chain operators Chaoshifa and Wumart.

The temperature screening solution being deployed in supermarkets, known as “Koala”, is an upgraded version of the company’s earlier product, consisting of a simple and user-friendly display pad that can be installed on the wall or on a stand, together with a small, portable processing unit. The solution has been designed for tight access control locations with low to medium foot flow, such as in a supermarket setting where customers line up and enter one by one.

The algorithms for the Koala solution have also been optimized through Megvii’s new generation AI productivity platform, Brain ++, and its proprietary deep learning framework, MegEngine. The system can accurately detect the forehead of incoming customers and check their temperature within a distance of 0.3 metres to one metre within half a second, with an accuracy level of ±0.3℃. The system alerts the administrator of individuals with high temperature, who may need to be taken aside for additional manual screening, and those who are not wearing a mask, which is mandatory in many public places.

Temperature screening in public places has served as the first line of defence in China’s efforts to contain the spread of COVID-19, as life gradually resumes in many Chinese cities.

The Koala solution improves temperature screening accuracy, while reducing the risk of transmission between supermarket staff and customers, and among customers, as it requires no physical contact. It also improves customer flow at supermarket entrances, ensuring people can move along quickly and do not have to wait in a queue.

The solution has received widespread recognition from users. "We use Megvii’s Koala solution to screen our own staff and customers, enhancing the overall security of our store. The solution offers an excellent user experience thanks to its high detection speed and accuracy even at a distance, and it is very easy to install and use," said a store manager from Chaoshifa.

To date, Megvii has deployed temperature screening solutions in various locations including convenience stores and supermarkets, residential and commercial buildings, hospitals, subway stations, and campuses to facilitate the re-opening of businesses and schools.  

Megvii’s Koala solution is widely deployed at supermarkets in Beijing

About Megvii Technology Limited

Megvii is a world-class AI company with core competencies in deep learning. Founded in Beijing in 2011 by Yin Qi, Tang Wenbin and Yang Mu, three Tsinghua University graduates who studied under the Turing-prize winning Chinese computer scientist and computational theorist Andrew Chi-Chih Yao, Megvii is a pioneer in applying AI technology and computer vision algorithms to Internet of Things (IoT) use cases. The Company’s mission is to power humanity with AI. 

Megvii’s first commercialized AI product was a facial recognition solution. The Company has developed its new generation AI productivity platform Brain++, which includes a proprietary deep learning framework that functions as a unified underlying architecture and provides critical support tailored for the Company’s algorithm training and model improvement processes.

Leveraging its strong software-hardware integration capabilities, Megvii offers full stack solutions to its customers, and has achieved leading positions in several key vertical markets, including personal IoT, city IoT and supply chain IoT. Megvii is building an AI infrastructure to connect and empower various IoT devices, to solve real life problems and pain points encountered by customers in sectors including fintech, transportation, logistics and others. Megvii is dedicated to helping customers achieve specific goals such as user authentication and fraud reduction, traffic optimization, and labor efficiency gains. 

Headquartered in Beijing with over 2,300 employees, Megvii maintains four research and development centers in China.

For press queries, please contact: