Eye movement parameter monitoring fatigue detection method based on N-range image processing algorithm

Abstract

The invention discloses an eye movement parameter monitoring fatigue detection method based on an N-range image processing algorithm. The fatigue detection method comprises the following steps: 1) collecting and preprocessing a side eye image; 2) carrying out convolution operation through the cross convolution kernel to obtain a gradient activation graph of the eye; 3) carrying out threshold segmentation on the gradient activation graph, removing an area with an activation degree lower than a threshold, setting the area as 0, and keeping the rest areas unchanged; 4) calculating standard deviation projection graphs of the image in the column direction and the row direction; adopting an average threshold segmentation method for the standard deviation projection image, and reserving a row serial number and a column serial number which are larger than the average standard deviation as eye areas; 5) calculating the height-width ratio of the rectangular frame, and judging the opening and closing states of the eyes, and 6) analyzing the fatigue state. the method has the advantages that the translation rotation and scale deformation are avoided, the robustness is high, the noise resistanceand the illumination imbalance resistance are high, and the fatigue detection accuracy can be improved.

Description

technical field [0001] The invention relates to the technical field of fatigue detection, in particular to a fatigue detection method for eye movement parameter monitoring based on an N-range image processing algorithm. Background technique [0002] Fatigue is a physiological phenomenon caused by excessive physical or mental work, and is a normal physiological activity rule of the human body. In medicine, fatigue is defined as a feeling of tiredness and lethargy in the human body, which is a signal for rest and relaxation. Fatigue is mainly manifested as drowsiness, lack of concentration, slowing down of the normal response of the human body, weakening of sympathetic nerve activity, and enhancement of parasympathetic nerve. Certain physiological, psychological, and behavioral science indicators of fatigue can be measured experimentally. For example, muscle fatigue is measured by electromyography, mental fatigue is measured by electroencephalogram and flash fusion frequency...

AI Technical Summary

Problems solved by technology

This method has high accuracy in state discrimination, but its practicability is low. The human eye is only divided into three states, and a large amount of human eye micro-motion information is lost. In terms of fatigue judgment, the accuracy rate is low.

At present, eye movement-based fatigue monitoring methods generally have defects such as large amount of calculation, low robustness, and low accuracy.

Images