Fatigue driving detection method based on depth information and fatigue driving detection device thereof

Abstract

The invention discloses a fatigue driving detection method based on depth information. The fatigue driving detection method comprises the steps that a color data frame or an infrared data frame including a driver image, a depth data frame, a human body index frame and a face frame are acquired through Kinect; the human body index frame is mapped to the depth data frame, the data point depth values belonging to the same human body index number on the depth data frame are added to obtain a mean value, and the corresponding human body index number of the least mean value is taken as the driver index number; the corresponding face frame is acquired according to the driver index number; information of five sense organs is acquired from the face frame to be drawn on the color data frame or the infrared data frame; and the closed eye situation is acquired according to the eye image of the color data frame or the infrared data frame and the PERCLOS value is calculated, and the fatigue driving prompt is given when the PERCLOS value exceeds the preset threshold. The invention also discloses a fatigue driving detection device based on the depth information. According to the method, the interference of the human body data of other persons apart from the driver can be eliminated by using the depth data so that the accuracy of fatigue detection is high.

Description

technical field [0001] The present invention relates to a fatigue driving detection method and device, in particular to a fatigue driving detection method and device based on depth information. Background technique [0002] Fatigue driving refers to the phenomenon that the driver's driving skills decline due to factors such as long-term driving, lack of sleep, or physical discomfort caused by blurred vision, slow response, distraction, and stiff movements. Fatigue driving is an important hidden danger of road traffic safety, so there is no shortage of designs for detecting and reminding fatigue driving in the prior art, so as to reduce the occurrence of fatigue driving and traffic accidents. [0003] Existing fatigue detection technologies include contact detection and non-contact detection. The contact detection system has a complex structure and is easy to interfere with the driver. Therefore, non-contact detection is generally used in fatigue driving detection. Non-cont...

AI Technical Summary

Problems solved by technology

[0006] In view of the deficiencies in the prior art above, the purpose of the present invention is to provide a fatigue driving detection method based on depth information, which solves the problem that multiple human head images appear in the detection image when many people are riding, and the detection accuracy is reduced when there are multiple pairs of eyes. The problem

Images