Fatigue driving detection method, automobile data recorder and storage device

Abstract

The invention discloses a fatigue driving detection method, an automobile data recorder and a storage device. The fatigue driving detection method comprises the following steps of: starting a camera to shoot face images; reading a frame of face image and preprocessing the face image; carrying out face detection on the preprocessed image by adoption of an Ada boost algorithm-based Haar classifier,and drawing a face box; predicting coordinate information of 16 key points around the eyes and mouth according to the face box; calculating eye areas according to the detected coordinate information of the key points, extracting HOG features of left and right eye areas, sending the HOG features into an SVM classifier and judging whether the eyes are in a closed state; and carrying out statistic onframe numbers of face images with closed eyes in a predetermined frames of face images, and if the frame number of the face images with closed eyes exceeds a predetermined threshold value, judging fatigue driving and outputting a fatigue alarm signal. The method has the advantages of suppressing interferences in the process of detecting the blink conditions of drivers and correctly judging the fatigue state of the drivers.

Description

technical field [0001] The invention relates to the field of motor vehicle fatigue driving detection methods, in particular to a fatigue driving detection method, a driving recorder and a storage device. Background technique [0002] With the rapid increase of the number of automobiles in our country, our country is facing unprecedented road traffic safety problems. Fatigue driving is one of the main causes of traffic accidents. According to statistics, about 30% of traffic accidents are caused by driver fatigue. Timely and effective detection of fatigue state and sending out alarm signals can minimize traffic accidents caused by fatigue driving. [0003] Fatigue detection methods are mainly divided into two types: contact and non-contact. The method of using sensors to monitor the driver's physiological signals to obtain pulse signals, electroencephalogram, electrocardiogram, electromyogram, respiratory rate and other physiological indicators to analyze the fatigue state ...

AI Technical Summary

Problems solved by technology

A non-contact fatigue detection method is to use computer vision methods to detect and analyze the driver's facial state, such as analyzing the driver's blinking, yawning, head state, etc., wherein when analyzing the driver's blinking, the traditional gray-based The methods of degree projection, centroid or edge detection are easily interfered by items worn by the driver, such as black-rimmed eyes.

Images