Fatigue driving monitoring device and method

Abstract

The invention provides a fatigue driving monitoring device and a fatigue driving monitoring method. The fatigue driving monitoring method comprises the steps of: 1) acquiring an acquired image; 2) converting the acquired image into a YCbCr space, extracting a skin color region and carrying out binarization to obtain a face rectangular frame; 3) scanning pixel points in the face rectangular frame, increasing radius by taking each pixel point as a circle center, finishing the scanning until the pixel points exceeding a preset proportion in the scanning regions are white points or the scanning regions reach the boundary of the face rectangular frame, and regarding the diameter of a maximum scanning regions as pupil diameter; 4) and judging whether a driver is fatigued through monitoring the pupil size in real time according to a PERCLOS algorithm. The fatigue driving monitoring device and the fatigue driving monitoring method can form the face rectangular frame in the YCbCr space quickly, simply and accurately, and detects the fatigue state of the driver through combining the real-time pupil size monitoring with the PERCLOS fatigue detection method. The fatigue driving monitoring device and the fatigue driving monitoring method are simple and efficient, fast in operation speed and high in accuracy, and the monitoring process and result are not affected by the inclination angle of face.

Description

technical field [0001] The invention relates to the field of face detection technology and fatigue driving detection technology based on eye fatigue feature detection, in particular to a fatigue driving monitoring device and method. Background technique [0002] The 2013 "Global Road Safety Status Report" shows that traffic accidents are the eighth leading cause of death in the world. About 1 million people die in traffic accidents every year in the world. Further statistical analysis shows that fatigue driving is the It is one of the important causes of traffic accidents, so it is necessary to detect and alarm fatigue. [0003] Methods for detecting drowsy driving can be broadly classified into three categories: [0004] 1. Based on the detection of vehicle driving status, such as detecting whether the vehicle deviates from the driving track; [0005] 2. Detection based on the driver's physiological parameters, such as the detection of the driver's EEG, ECG, etc.; [000...

AI Technical Summary

Problems solved by technology

[0011] However, the general face detection algorithm is more complicated, and the real-time performance is not so good, especially when the face is tilted at a relatively large angle.

Images