Drowsiness mental state analysis using blink rate
Drowsiness mental state analysis is performed using blink rate. Video is obtained of an individual or group. The individual or group can be within a vehicle. The video is analyzed to detect a blink event based on a classifier, where the blink event is determined by identifying that eyes are closed for a frame in the video. A blink duration is evaluated for the blink event. Blink-rate information is determined using the blink event and one or more other blink events. The evaluating can include evaluating blinking for a group of people. The blink-rate information is compensated to determine drowsiness, based on the temporal distribution mapping of the blink-rate information. Mental states of the individual are inferred for the blink event based on the blink event, the blink duration of the individual, and the blink-rate information that was compensated. The compensating is biased based on demographic information of the individual.
1. A computer-implemented method for mental state analysis comprising:
obtaining video of an individual with an image capture device;
analyzing, using one or more processors, the video to detect a blink event based on a classifier for a blink that was determined wherein the blink event is determined by identifying that eyes of the individual are closed for a frame in the video using temporal analysis;
evaluating, using the one or more processors, a blink duration of the individual for the blink event;
determining, using the one or more processors, blink-rate information using the blink event and one or more other blink events, wherein the determining yields a blink-rate frequency, wherein a higher blink-rate frequency infers more drowsiness over the temporal distribution of the blink-rate information;
compensating, using the one or more processors, the blink-rate information to determine drowsiness, based on a temporal distribution of the blink-rate information; and
inferring, using the one or more processors, mental states of the individual for the blink event, wherein the mental states are based on the blink event, the blink duration of the individual, and the blink-rate information that was compensated.
2. The method of claim 1 wherein a longer blink duration infers more drowsiness over the temporal distribution of the blink-rate information.
3. The method of claim 1 further comprising biasing the compensating based on demographic information of the individual.
4. The method of claim 3 wherein the demographic information includes one or more of ethnicity, age, or gender.
5. The method of claim 1 wherein the individual is a passenger in a vehicle.
6. The method of claim 1 wherein the individual is a driver of a vehicle.
7. The method of claim 6 wherein the driver is a custodial driver.
8. The method of claim 1 further comprising manipulating a vehicle based on the mental states that were inferred.
9. The method of claim 8 wherein the manipulating the vehicle includes recommending action.
10. The method of claim 8 wherein the manipulating the vehicle includes initiating a locking out operation, recommending a break for an occupant, recommending a different route, recommending how far to drive, controlling the vehicle in response to traffic, adjusting seats, adjusting mirrors, adjusting climate control, adjusting lighting, adjusting music, generating audio stimuli, activating a braking system, or activating steering control.
11. The method of claim 8 wherein the manipulating the vehicle includes recommending content to the individual.
12. The method of claim 1 wherein the image capture device includes a near-infrared image capture device.
13. The method of claim 1 further comprising locating a portion of a face with eyes.
14. The method of claim 13 further comprising performing temporal analysis on the portion of the face to identify that the eyes are closed.
15. The method of claim 1 further comprising determining a difference in blinking by the individual and typical blinking for the individual.
16. The method of claim 15 wherein the inferring mental states of the individual is further based on the difference in blinking by the individual and typical blinking for the individual.
17. The method of claim 1 wherein the analyzing filters out single eye winks or looking down by the individual.
18. The method of claim 1 further comprising evaluating average blink duration.
19. The method of claim 1 further comprising evaluating blinking for a group of people of which the individual is a part.
20. The method of claim 19 further comprising determining a difference in blinking between the individual and a remainder of the group.
21. The method of claim 1 further comprising aggregating the blink-rate information for the individual with blink-rate information for a plurality of other people.
22. The method of claim 1 further comprising correlating the blink-rate information with activities performed by the individual.
23. A computer program product embodied in a non-transitory computer readable medium for mental state analysis, the computer program product comprising code which causes one or more processors to perform operations of:
obtaining video of an individual with an image capture device;
analyzing, using one or more processors, the video to detect a blink event based on a classifier for a blink that was determined wherein the blink event is determined by identifying that eyes of the individual are closed for a frame in the video using temporal analysis;
evaluating, using the one or more processors, a blink duration of the individual for the blink event;
determining, using the one or more processors, blink-rate information using the blink event and one or more other blink events, wherein the determining yields a blink-rate frequency, wherein a higher blink-rate frequency infers more drowsiness over the temporal distribution of the blink-rate information;
compensating, using the one or more processors, the blink-rate information to determine drowsiness, based on a temporal distribution of the blink-rate information; and
inferring, using the one or more processors, mental states of the individual for the blink event, wherein the mental states are based on the blink event, the blink duration of the individual, and the blink-rate information that was compensated.
24. A computer system for mental state analysis comprising:
a memory which stores instructions;
one or more processors coupled to the memory wherein the one or more processors, when executing the instructions which are stored, are configured to:
obtain video of an individual with an image capture device;
analyze the video to detect a blink event based on a classifier for a blink that was determined wherein the blink event is determined by identifying that eyes of the individual are closed for a frame in the video using temporal analysis;
evaluate a blink duration of the individual for the blink event;
determine blink-rate information using the blink event and one or more other blink events, wherein the determination yields a blink-rate frequency, wherein a higher blink-rate frequency infers more drowsiness over the temporal distribution of the blink-rate information;
compensate the blink-rate information to determine drowsiness, based on a temporal distribution of the blink-rate information; and
infer mental states of the individual for the blink event, wherein the mental states are based on the blink event, the blink duration of the individual, and the blink-rate information that was compensated.