Eyesight Technologies in-car monitoring upgraded for accuracy with facemasks
The U.S. Centers for Disease Control and Prevention recently advised that people should be wearing masks when in public to help contain COVID-19, a measure especially applicable to essential workers in government, and truck and bus drivers. Following this recommendation, Eyesight Technologies has upgraded its platform for in-cabin sensing solutions to detect when drivers who wear face masks get distracted or feel fatigued behind the wheel, writes VentureBeat.
Truck and bus drivers usually have longer drive times which makes them more prone to fatigue. The Federal Motor Carrier Safety Administration revoked the 11-hour-a-day cap for drivers carrying emergency supplies in March.
“We are living in unprecedented times,” said Eyesight CEO David Tolub, in a prepared statement. “Without a concrete end date to the current situation, wearing medical masks may be a reality for the foreseeable future. Eyesight … is forging ahead and adapting to provide a reliable solution to help guarantee safety even under less than ideal circumstances.”
Eyesight Technologies has developed a set of AI algorithms that can keep track of drivers’ behavior behind the wheel when wearing masks or sunglasses. The company’s Driver Sense and Fleet Sense leverage IR sensors to analyze head position, eye openness, pupil dilation, blink rate, and gaze direction, in any lighting use case.
“Traditionally, [our systems] would … track certain factors on the mouth and face, but we have actively trained our AI and computer vision on use cases with a face mask to be able to perform even with these occluded,” an Eyesight spokesperson told VentureBeat via email. “We had to collect large amounts of data of drivers wearing various face masks in different driving scenarios. This is something that we had a headstart on while building our system for the Asian market, where masks have always been more prevalent.”
Since the coronavirus outbreak, a number of biometric companies have upgraded their technology to be operational and accurate when surgical masks are worn. Corsight, SAFR, Innovatrics, Speech Technology Center, NEC, Telpo, Alibaba, ZKTeco USA, SenseTime, Herta, and Hanvon have all claimed their biometric recognition algorithm adapts to work with masks.