Direct observation event triggering of drowsiness

• US 8,952,819 B2
• Filed: 01/31/2013
• Issued: 02/10/2015
• Est. Priority Date: 01/31/2013
• Status: Active Grant

• Current Assignee: Lytx, Inc.
• Original Assignee: Lytx, Inc.
• Inventors: Nemat-Nasser, Syrus C.
• Primary Examiner(s): Previl, Daniel
• Application Number:
  US13/755,194
• Publication Number:
  US 20140210625A1
• Time in Patent Office: 740 Days
• Field of Search: 340575-576, 340/573.1, 340/435, 340/425.1, 340472-474, 340/511, 340/539.12, 340/539.18, 340/632, 340/692
• US Class Current: 340/575
• CPC Class Codes: B60K 28/066 actuating a signalling device B60K28/063 takes precedence
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms

Abstract

A system for event triggering comprises an interface and a processor. An interface configured to receive a face tracking data and receive a sensor data. The processor configured to determine a degree of drowsiness based at least in part on the face tracking data and the sensor data; in the event that the degree of drowsiness is greater than a first threshold, capture data; and in the event that the degree of drowsiness is greater than a second threshold, provide a warning.

Claims

1. A system for event triggering, comprising:

an interface configured to;

receive a face tracking data;

receive a sensor data; and

a processor configured to;

determine a degree of drowsiness based at least in part on the face tracking data and the sensor data, wherein the degree of drowsiness is determined using a model;

in the event that the degree of drowsiness is greater than a first threshold, capture data of a drowsy driving event; and

in the event that the degree of drowsiness is greater than a second threshold, provide a warning;

determine a score for the drowsy driving events based at least in part on a review of captured data of drowsy driving events;

update the model for determining the degree of drowsiness based at least in part on the score of the drowsy driving events.

2. A system as in claim 1, wherein the model is one of the following:

rule-based model, statistical model, neural network based model, or an automatically calibrating anomaly detection model.

3. A system as in claim 1, wherein the model is trained using one or more of the following:

driving simulator data, video data, sensor data, audio data, or captured data.

4. A system as in claim 1, wherein the model is used to determine a drowsy driving behavior using only non-face-data sensors.

5. A system as in claim 1, wherein the model is used to determine a real-time driver warning using only non-face-data sensors.

6. A system as in claim 1, wherein the face tracking data comprises a blink duration.

7. A system as in claim 6, wherein the blink duration is relative to a driver specific blink duration baseline.

8. A system as in claim 7, wherein the driver specific baseline includes an average blink duration and a standard deviation of blink duration.

9. A system as in claim 1, wherein the face tracking data comprises head nodding.

10. A system as in claim 9, wherein the head nodding is relative to a driver specific head nodding baseline.

11. A system as in claim 10, wherein the driver specific baseline includes an average head nodding and a standard deviation of head nodding.

12. A system as in claim 1, wherein the face tracking data is captured using a rear-view mirror mounted unit.

13. A system as in claim 1, wherein sensor data comprises one or more of the following:

steering data, acceleration data, braking data, application of gas data, deviations data, jerkiness of responses data, corrections data, or overcorrections data.

14. A system as in claim 1, wherein capturing data comprises capturing data prior to being triggered by the drowsiness degree, during the trigger by the drowsiness degree, and after the trigger by the drowsiness degree.

15. A system as in claim 1, wherein the driver is warned using one or more of the following an audible warning, an illumination warning, or a haptic warning.

16. A system as in claim 1, wherein the processor is further configured to warn one or more of the following:

a dispatcher, a system administrator, or a supervisor.

17. A system as in claim 1, wherein the first threshold or the second threshold is dynamically adjusted.

18. A method of event triggering, comprising:

receiving a face tracking data;

receiving a sensor data;

determining a degree of drowsiness based at least in part on the face tracking data and the sensor data, wherein the degree of drowsiness is determined using a model; and

in the event that the degree of drowsiness is greater than a first threshold, capturing data of a drowsy driving event; and

in the event that the degree of drowsiness is greater than a second threshold, providing a warning;

determining a score for the drowsy driving events based at least in part on a review of captured data of drowsy driving events;

updating the model for determining the degree of drowsiness based at least in part on the score of the drowsy driving events.

19. A computer program product for event triggering, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

receiving a face tracking data;

receiving a sensor data;

determining a degree of drowsiness based at least in part on the face tracking data and the sensor data, wherein the degree of drowsiness is determined using a model; and

in the event that the degree of drowsiness is greater than a first threshold, capturing data of a drowsy driving event; and

in the event that the degree of drowsiness is greater than a second threshold, providing a warning;

determining a score for the drowsy driving events based at least in part on a review of captured data of drowsy driving events;

updating the model for determining the degree of drowsiness based at least in part on the score of the drowsy driving events.