DROWSINESS DETECTION METHOD AND APPARATUS THEREOF

• US 20100168591A1
• Filed: 12/23/2009
• Published: 07/01/2010
• Est. Priority Date: 12/31/2008
• Status: Abandoned Application

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: HUANG, YUAN MEI, SU, YU JEN, CHEN, NING HUNG, TAO, TEH HO, CHOW, ZU SHO
• Application Number:
  US12/646,811
• Publication Number:
  US 20100168591A1
• Time in Patent Office: Days
• US Class Current: 600/500
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators

Abstract

The apparatus comprises an ultra-wide band module or an electrocardiography module for gathering heartbeat signals of a human being. By sequentially obtaining average heart-rate values of a human being, and according to the features of the heart-rate values over a period of time, the method is utilized to determine whether the human being is going to a state of drowsiness.

Claims

1. A drowsiness detection method, comprising:

detecting a plurality of physiological feature values of an object and storing the plurality of physiological feature values into a queue;

obtaining a plurality of specific values from the queue, wherein the plurality of specific values comprise a first minimum value, a second minimum value, a first maximum value, and a value of a first position; and

obtaining a plurality of difference values between the plurality of specific values and comparing the plurality of difference values with at least one threshold value to generate a drowsiness detection result.

2. The method of claim 1, wherein the plurality of physiological feature values are obtained according to peak numbers of a plurality of sequential signals of the object.

3. The method of claim 1, wherein the plurality of physiological feature values are a plurality of heartbeat frequencies or a plurality of pulse frequencies.

4. The method of claim 1, wherein the first minimum value is a first local minimum value found from the front of the queue.

5. The method of claim 1, wherein the second minimum value is a minimum value obtained within a queue length by searching from a position of the first minimum value of the queue.

6. The method of claim 1, where the first maximum value is a maximum value obtained within a queue length by searching from the position of the first minimum value of the queue.

7. The method of claim 1, wherein the plurality of difference values comprise a first difference value between the value of the first position and the first minimum value, and a second difference value between the first maximum value and the first minimum value.

8. The method of claim 7, further comprising a step of generating an alarm message and deleting all stored values in the queue if the first difference value is greater than or equal to a first threshold value and the second difference value is less than or equal to a second threshold value.

9. A drowsiness detection method, comprising:

detecting a plurality of physiological feature values of an object and storing the plurality of physiological feature values into a queue;

obtaining a maximum value, a first minimum value, and a second minimum value in the queue; and

obtaining a plurality of difference values between the maximum value, the first minimum value, and the second minimum value, and comparing the plurality of difference values with a plurality of threshold values to generate a drowsiness detection result.

10. The method of claim 9, wherein the plurality of physiological feature values are obtained according to peak numbers of a plurality of sequential signals of the object.

11. The method of claim 9, wherein the plurality of physiological feature values are a plurality of heartbeat frequencies or a plurality of pulse frequencies.

12. The method of claim 9, wherein the first minimum value and the second minimum value are minimum values obtained by searching from the front of the queue to a position of the maximum value and from the end of the queue to the position of the maximum value, respectively.

13. The method of claim 9, wherein the plurality of difference values comprise a first difference value and a second difference value, wherein the first difference value is a difference value between the maximum value and the first minimum value and a second difference value is a difference value between the maximum value and the second minimum value.

14. The method of claim 13, further comprising a step of generating an alarm message and deleting all the stored values of the queue if the first difference value is greater than or equal to a first threshold value and the second difference value is smaller than or equal to a second threshold value.

15. A drowsiness detection method, comprising:

detecting a plurality of physiological feature values of an object and storing the plurality of physiological feature values in first and second queues;

obtaining a first maximum value, a first minimum value, and a second minimum value of the first queue;

obtaining a difference value between the first maximum value and the first minimum value and comparing the difference with a first threshold value and obtaining a difference value between the maximum value and the second minimum value and comparing the difference with a second threshold value, respectively, to generate a first comparison result;

obtaining a difference value between a second maximum value and a third minimum value of the second queue and comparing the difference with a third threshold value to generate a second comparison result; and

generating a drowsiness detection result according to the first and second comparison results.

16. The method of claim 15, wherein the plurality of physiological feature values are obtained according to peak numbers of a plurality of sequential signals of the object.

17. The method of claim 15, wherein the plurality of physiological feature values are a plurality of heartbeat frequencies or a plurality of pulse frequencies.

18. The method of claim 15, wherein the first maximum value is a maximum value of the first queue.

19. The method of claim 15, wherein the first minimum value and the second minimum value are minimum values obtained by searching from the front of the first queue to a position of the first maximum value and from the end of the first queue to the position of the first maximum value, respectively.

20. The method of claim 15, wherein the second maximum value is a maximum value of the second queue.

21. The method of claim 15, wherein the third minimum value is a minimum value of the second queue.

22. The method of claim 15, further comprising a step of generating a first comparison result and deleting all the stored values of the first queue if a difference value between the first maximum value and the first minimum value is greater than or equal to the first threshold value while a difference value between the first maximum value and the second minimum value is greater than or equal to the second threshold value.

23. The method of claim 22, further comprising a step of generating a second comparison result if a difference value between the second maximum value and the third minimum value is less than or equal to the third threshold value.

24. The method of claim 23, further comprising a step of generating an alarm message when the first comparison result is generated before the second comparison result while the period of the first and second comparison results is less than or equal to a time interval.

25. A drowsiness detection apparatus, comprising:

a signal detection unit configured to obtain a plurality of sequential signals of an object during a plurality of time intervals; and

an operation module configured to convert the plurality of sequential signals into a plurality of frequencies and to obtain mutual relationships of the plurality of frequencies, so as to generate a drowsiness detection result.

26. The apparatus of claim 25, further comprising a storage medium configured to store the plurality of frequencies.

27. The apparatus of claim 25, further comprising an alarm configured to generate a plurality of messages according to the drowsiness detection result.

28. The apparatus of claim 25, wherein the operation module is configured to convert peak numbers of the plurality of sequential signals into the plurality of frequencies.

29. The apparatus of claim 25, wherein periods of the plurality of time intervals can be the same, partially different, or totally different.

30. The apparatus of claim 25, wherein the plurality of frequencies are a plurality of heartbeat frequencies or a plurality of pulse frequencies.

31. The apparatus of claim 25, wherein the plurality of frequencies are average frequencies during the plurality of time intervals.

32. The apparatus of claim 25, wherein the signal detection unit comprises:

an ultra-wide band antenna configured to emit a plurality of ultra-wide band signals; and

a receiver configured to receive reflected signals after the plurality of ultra-wide band signals pass through the object and to obtain the plurality of sequential signals during the plurality of time intervals.

33. The apparatus of claim 25, wherein the signal detection unit comprises an electrocardiography module.