Name
Abstract | ||
|---|---|---|
Drowsiness and lapses of responsiveness have the potential to cause fatalities in many occupations. One subsystem of a prototype device which aims to detect these lapses as they occur is described. A head-mounted camera measures several features of the eye that are known to correlate with drowsiness. The system was tested with eight combinations of eye colour, ambient lighting, and eye glasses to simulate typical real-world input conditions. A task was completed for each set of conditions to simulate a range of eye movement-saccades, tracking, and eye closure. Our image processing software correctly classified 99.3% of video frames as open/closed/partly closed, and the error rate was not affected by the combinations of input conditions. Most errors occurred during eyelid movement. The accuracy of the pupil localisation was also not influenced by input conditions, with the possible exception of one subject's glasses. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/EMBC.2013.6611072 | EMBC |
Keywords | Field | DocType |
eye,biomechanics,eye dynamics measurement,eye feature measurement,biomedical optical imaging,image processing software,eyelid movement,eye colour,head-mounted camera,eye closure,image classification,eye tracking,cameras,eye saccade,wearable device,video frame classifcation,eye ambient lighting,medical image processing,eye glass,hardware,lighting,glass,eye movements,image processing | Computer vision,Computer science,Wearable computer,Word error rate,Eye tracking on the ISS,Pupil,Eye movement,Software,Eye tracking,Artificial intelligence,Contextual image classification | Conference |
Volume | ISSN | Citations |
2013 | 1557-170X | 0 |
PageRank | References | Authors |
0.34 | 4 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Simon Knopp | 1 | 0 | 0.34 |
| Philip J. Bones | 2 | 12 | 4.80 |
| S. J. Weddell | 3 | 13 | 5.76 |
| Carrie R. H. Innes | 4 | 20 | 3.59 |
| Richard D. Jones | 5 | 58 | 9.10 |