Human Operator Gaze Movement Characteristics Analysis for Fatigue Detection

Abstract

The paper investigates relationships between gaze movement characteristics and human fatigue. Gaze movement characteristics are calculated from such basic concepts of gaze as fixation and saccade. Characteristics can also be divided by the types of physical events on which they are based. It is possible to distinguish such characteristics as speed, time, quantity, size, percentage, frequency, and ratio characteristics. To search for correlations between gaze movement characteristics and fatigue, a dataset of gaze movements and the results of the VAS-F fatigue questionnaire were analyzed in 10 subjects. The dataset consists of operator parameters such as gaze movements, scene camera image, and gaze direction. To detect the level of fatigue, the participant completed the VAS-F questionnaire. Each record from the dataset corresponds to a questionnaire result. A total of 60 characteristics of eye movements and the corresponding VAS-F test values were analyzed and the correlation between them was calculated. The characteristics of eye movements were then sorted in descending order of the obtained correlation values. For further analysis, the first 20 characteristics with the highest correlation were selected from each participant. A search was then made for characteristics that were found in 60% or more of the participants among the first 20 characteristics. As a result, 9 characteristics of eye movements were found that correlated with VAS-F test scores for each participant. The significant correlation was shown by speed characteristics, size characteristics, time characteristics, frequency characteristics, ratio characteristics, and proportion characteristics.

Keywords

• fatigue detection
• eye traking data
• gaze movement