Citation

Nie B, Huang X, Chen Y, Li A, Zhang R, Huang J. Appl. Ergon. 2017; 65: 1-11.

Affiliation

School of Resources and Safety Engineering, China University of Mining and Technology (Beijing), D 11, Xueyuan Road, Haidian District, Beijing, 100083, China; State Key Lab of Coal Resources and Safe Mining, China University of Mining and Technology (Beijing), D 11, Xueyuan Road, Haidian District, Beijing, 100083, China.

Copyright

(Copyright © 2017, Elsevier Publishing)

DOI

10.1016/j.apergo.2017.05.010

PMID

28802427

Abstract

Fatigue can lead to decreased work performance and poorer safety and health condition. Fatigue is ubiquitous in production and in life, while the research on it is mainly concentrated in the automotive driving, aircraft piloting and other fields, and it is insufficient to study on the fatigue of fixed-position staff. This paper puts forward a non-contact visual image method, which can monitor the extent of fatigue of fixed-position staff. Fatigue threshold used in judgment is obtained by processing the recorded data of visual images of the experimental subjects when fatiguing and by analyzing eye closure time, percentage of eyelid closure (PERCLOS) value, frequency and number of blinks. The results show that there is significant difference among the four indicators before and after experiment subjects undergo fatigue. The fatigue of experimental subjects is obvious when eye closure time is 3.5 s/min, PERCLOS value 6%, and blink frequency 0.4 times/s. This provides a reference for a wider range of detection of fatigue and a method for avoiding mistakes and accidents.

Copyright © 2017 Elsevier Ltd. All rights reserved.

Language: en

Keywords

Fatigue; Image processing; PERCLOS