Posted 2021-10-03 00:00:00 +0000 UTC
According to foreign media reports, recently, eye technologies, an AI computer vision solution developer, and Ariel University in Israel announced cooperation on the University's M-Lab project. In this collaboration, Ariel University will provide eye technologies with its unique data set to study driver status. (photo source: eyes technologies official website) M-Lab is an interdisciplinary research cooperation project operated by experts in computer science, robotics and human experience of Ariel University, focusing on the design of user interface, feedback system and driver intervention mode. The purpose of M-Lab is to use the sensor array of the test vehicle to test the real driving scene. M-Lab researchers use sensors to collect road and external driving environment data and monitor driver status, such as brain load, stress detection (skin conduction), alertness (steering wheel grip), fatigue (heart rate, respiration, face and eye tracking), and road attention (face and eye tracking). The M-Lab test vehicle is equipped with driver sense, a driver monitoring system of eyes technologies, to obtain accurate monitoring data related to the driver's face and eyes. Eye technologies monitors the driver's eye opening, blinking frequency, gaze direction and head posture, as well as other factors that determine the driver's driving status. Eyesight technologies is using M-Lab's field test data and various sensor data to obtain valuable information about the driver's status, so as to further evaluate, monitor and improve its driver monitoring solution. This important information comes from sensor fusion and data collaboration among all available systems, rather than a single driver monitoring sensor data. The M-Lab project uses the precise vision layer of eyes technologies to detect and track the head posture and obtain various eye related data, which can be used for multiple projects, such as checking the driver's ability to use semi-automatic cruise system to re control the vehicle under different mental load conditions, and can also be used to prove the concept of "reliable automation".
Copyright © 2020. TUTESL All rights reserved.