With the growing scare of the deadly coronavirus, companies in China are pushing hard to limit its spread. In one such effort, the country’s leading search engine Baidu has open-sourced an AI model to detect people not wearing face masks.
As coronavirus can spread through close contact with an infected person via their coughs, sneezes, or respiratory droplets, China has made it mandatory to wear face masks in several regions. People are instructed to wear masks in public places such as restaurants, shopping malls, and public transport.
It’s quite hard for authorities to catch people not wearing masks in large crowds. That’s where Baidu’s tool will be useful. The company said it had trained the model on more than 100,000 images to achieve prediction accuracy of 96.5%.
As many factories and businesses in China have resumed work after the Lunar New Year holiday, it’s important for companies to identify people not wearing masks to limit the spread of the virus.
According to the World Health Organization (WHO), over 51,000 confirmed cases have been registered in China, with death toll crossing 1,600.
Last week, the Chinese government launched an app to help people know if they have come in close contact with anyone affected by the virus.
Companies in China are trying to provide tools and funding to fuel research to find the deadly virus’ cure. Earlier this month, Baidu and e-commerce giant Alibaba open-sourced AI models for university and medical centers to improve prediction times for RNA structure of the virus.
You’re here because you want to learn more about artificial intelligence. So do we. So this summer, we’re bringing Neural to TNW Conference 2020, where we will host a vibrant program dedicated exclusively to AI. With keynotes by experts from companies like Spotify, RSA, and Medium, our Neural track will take a deep dive into new innovations, ethical problems, and how AI can transform businesses. Get your early bird ticket and check out the full Neural track.
Get the TNW newsletter
Get the most important tech news in your inbox each week.