KT powertel releases solution capable of monitoring driver's status

By Lim Chang-won Posted : October 15, 2020, 16:16 Updated : October 15, 2020, 16:16

[Courtesy of KT powertel]


SEOUL -- For vehicle management by corporate customers, KT powertel, a subsidiary of South Korea's top telecom company KT, worked with Movon, a producer of video-based advanced driver assistance systems, to release a solution capable of monitoring the status of drivers in real-time.

The solution called "Power Driver Status Monitoring (DSM)" prevents accidents by looking at pupils and facial expressions through a terminal installed in the vehicle to sound an alarm when the driver dozes off at the wheel or does not look ahead. Korea Zinc, a domestic non-ferrous metal smelting company, would be the first adopter of Power DSM.

KT powertel said that the solution senses sideways with a full face contour and 83 coordinates including eyes, nose and mouth. It detects real-time accident risk behaviors such as drowsy driving, cell phone use and smoking. Near-infrared cameras allow for smooth recognition even in dark environments.

If a warning occurs at a terminal, related data will be sent to the server through an IoT solution. A control program can check and improve driving habits. "It will be an essential on-site IoT solution that helps corporate customers reduce operating costs through streamlining vehicle management," said KT powertel CEO Kim Yoon-soo.

According to Korea Express Corporation, South Korea's expressway operator, about 60 percent of fatal road accidents in 2018 were caused by drowsy driving. Dozing off behind the wheel is extremely dangerous as it is hard for drivers to recognize if he or she is falling asleep. The majority of accidents caused by drowsy driving take place on expressways where cars travel at high speed.

In December 2019, a research team from Seoul National University Bundang Hospital developed a new algorithm that analyzes brainwaves to predict whether the driver will fall into a nod within two seconds by adopting machine learning. 
 
기사 이미지 확대 보기
닫기