Human eye state rapid identification method based on mesh region segmentation and threshold adaptation

Abstract

The invention discloses a human eye state rapid identification method based on mesh region segmentation and threshold adaptation. The geometric region of the human eye position is located by using an Adaboost algorithm, and the eye pupil feature region is calibrated by grid trichotomy; a binary algorithm for adaptively obtaining the background image separating optimum threshold value is adopted to perform black and white enhancement on the images in the three areas of the eye part; the standard formula for calculating the pupil closing degree is corrected to the formula for calculating the pupil closing degree by introducing the drift factor; and at the end, based on the PERCLOS method, whether one's eyes are in the fatigue state is determined. The method solves the problem that the human eye fatigue state identification accuracy is low because of the uncertainty of the image enhancement processing threshold caused by the front and rear frame eye image gray scale change caused by the pupil position change and illumination change resulted by the head rotation and frequent eye drift of a driver during the driving, and the occupied calculation resource is less and the real-time performance is high.

Description

technical field [0001] The invention relates to a recognition method of human eye state, in particular to a fast recognition method of human eye state based on grid area segmentation and threshold value self-adaptation, and belongs to the technical field of image processing and pattern recognition. Background technique [0002] According to statistics from the National Highway Traffic Safety Administration of the United States, about 100,000 traffic accidents are caused by fatigue driving every year; according to the traffic accident statistics of the French National Police Agency, accidents caused by fatigue and drowsiness account for 14.9% of personal injury accidents and 20.6% of fatal accidents. %; On the expressways in Germany, 25% of personal injury accidents are caused by fatigue driving. With the continuous and rapid increase in the number of motor vehicles in my country, the mileage of highways opened to traffic increases year by year, and the pace of modern life is...

AI Technical Summary

Problems solved by technology

This invention has a large amount of calculation and uses edge images. When the edge features are not obvious due to head rotation and uneven illumination, the recognition accuracy is not high, and an effective edge detection algorithm is needed.

Images