CLAIMS
1. A method of detecting a microsleep event in a subject, the method comprising: - determining a plurality of eye openness factors by measuring a plurality of distances between an upper eyelid and a lower eyelid of at least one eye over a time period;
- generating graphical representations of the eye openness factors; and
- correlating changes in the eye openness factors over the time period with a reference eye closure pattern indicative of the microsleep event.
2. The method, according to claim 1 , further comprising: illuminating the face of the subject; and recording a facial image.
3. The method, according to claim 2, in which a digital camera having an infra-red source is used to illuminate the face and to record the facial image.
4. The method, according to claim 1 , further comprising: identifying the eye and the eyelids by using a facial feature recognition algorithm.
5. The method, according to claim 1 , further comprising: verifying the presence of microsleep characteristic eye openness factor levels by measuring the eye openness factors as a function of time for a blink cycle of the eye.
6. The method, according to claim 5, in which the eye openness factors levels include at least one eye openness level.
7. The method, according to claim 5, in which the eye openness factors include one or more eye openness levels and five or less eye openness levels.
8. The method, according to claim 5, in which the eye openness factors include five eye openness levels.
9. The method, according to claim 5, in which the eye openness levels are associated with an open eye, the closure of the eyelids, partial or closed eye, and opening of the eyelids
10. The method, according to claim 1 , in which the eye openness factors include five successive eye openness levels, the sequential detection of the five levels being indicative of microsleep characteristics.
11. The method, according to claim 10, further comprising: determining additional eye openness factors if less than five successive eye openness factor levels are detected.
12. The method, according to claim 5, further comprising: computing eye opening and eye closure representative curves.
13. The method, according to claim 12, in which the eye closure representative curves are computed using a negative slope and a second order polynomial regression applied to the eye openness factors of the first and second eye openness factor levels.
14. The method, according to claim 12, in which the eye opening factors are computed using a positive slope and a second order polynomial regression applied to the eye openness factors of the fourth and fifth eye openness factor levels.
15. The method, according to claim 12, further comprising: verifying the presence of microsleep eye opening and closing representative curves by computing the Pearson coefficient of the eye closure representative curves with
regard to the first and second eye openness factor levels and the eye opening representative curves with regard to the fourth and fifth eye factor levels.
16. The method, according to claim 15, in which the subject is informed when the Pearson coefficients are greater than or equal to a predetermined threshold value.
17. The method, according to claim 3, in which images of the face are sampled at a frequency of between 10 Hz and 60Hz.
18. The method, according to claim 5, further comprising: a sub-process for detecting microsleep characteristic eye openness factor levels at an image sampling frequency of 20Hz.
19. The method, according to claim 18, in which the sub-process comprises: verifying that a first level is detected by confirming the presence of a series six or more successive eye openness factors corresponding to an open eye.
20. The method, according to claim 19, further comprising: verifying that a second level is detected by confirming the presence of a series four or more successive decreasing eye openness factors.
21. The method, according to claim 20, further comprising: verifying that a third level is detected by confirming the presence of a series of a minimum of five and a maximum of one-hundred and twenty successive eye openness factors.
22. The method, according to claim 21 , further comprising: verifying that a fourth level is detected by confirming the presence of a series of a minimum of four successive eye openness factors.
23. The method, according to claim 22, further comprising: verifying that a fifth level is detected by confirming the presence of a series of a minimum of six successive eye openness factors corresponding to the open eye.
24. The method, according to claim 1 , further comprising: alerting the subject to the presence of the microsleep event.
25. A microsleep event detection device, the device comprising:
- a facial image sampler for sampling facial images over time of a subject, the sampler having an infra red source for illuminating one or more eyes of the subject;
- a microprocessor having electronically stored therein an electronically executable microsleep detection process, the microprocessor being connected to the sampler for receiving the sampled facial images, the images being electronically converted to graphical representations of eye openness factors; and
- a memory associated with the microprocessor, the memory having stored therein a plurality of reference eye closure patterns for electronically correlating the eye openness factors with the reference eye closure patterns.
26. The device, according to claim 25, further comprising an alert connected to the microprocessor for alerting the subject to the microsleep event.
27. A method of alerting a vehjcle operator to a microsleep event, the method comprising:
- determining a plurality of eye openness factors by measuring a plurality of distances between an upper eyelid and a lower eyelid of at least one eye over a time period;
- generating graphical representations of the eye openness factors; - correlating changes in the eye openness factors over the time period with a reference eye closure pattern indicative of the microsleep event; and
- triggering an alarm so as to alert the operator to the microsleep event.
28. A method of correlating EEG and EOG microsleep patterns with eye closure patterns, the method comprising:
- measuring EEG and EOG microsleep patterns in a subject;
- determining a plurality of eye openness factors by measuring a plurality of distances between an upper eyelid and a lower eyelid of at least one eye over a time period;
- generating graphical representations of the eye openness factors; and
- correlating changes in the eye openness factors with the EEG and EOG microsleep patterns.
