A driver cognitive distraction monitoring method based on multi-source information fusion

Abstract

The invention relates to a driver cognitive distraction monitoring method based on multi-source information fusion, which belongs to the technical field of automobile active safety. The method includes: collecting steering wheel angle, vehicle speed, driver's head orientation, and gaze point coordinate information in real time; Arrange the real-time collected data into a data sequence according to time; according to the time-domain statistical indicator set (cognitive score) of the steering wheel angle, vehicle speed, driver's head orientation, and gaze point coordinates calculated within the calculation time window length, The cognitive distraction monitoring algorithm based on feature-level multi-source information fusion of support vector machines is used to monitor the driver's cognitive distraction state in real time, so as to improve driving safety and reduce road traffic accidents.

Description

technical field [0001] The invention belongs to the technical field of automobile active safety, and in particular relates to a driver's cognitive distraction state monitoring technology based on driver's operation information and eye movement information. Background technique [0002] In the road traffic system composed of people, motor vehicles, and road environment, the motor vehicle driver is a weak link in the system. The driving process is complex, including multiple links such as situation awareness, decision-making, and execution. It is inevitable that distraction errors, Sudden abnormalities such as wrong judgments directly lead to driving risks. There are many reasons for driver error, and inattention is one of the most important. The driver attention monitoring system is an advanced automotive driving assistance system. It monitors the driver's attention status in real time. When the driver's attention is low, it will directly give an alarm prompt and provide dri...

AI Technical Summary

Problems solved by technology

[0003] Existing attention monitoring systems are mostly aimed at low attention caused by fatigue that changes slowly, and distraction is highly time-varying and requires high real-time monitoring. The existing driver's attention monitoring cannot cope with this feature of distraction; Existing attention monitoring systems mostly focus on visual distraction, while cognitive distraction has complex performance, poor consistency of conclusions, and it is difficult to find common characteristics in different driving scenarios, making monitoring difficult

Images