Method for the classification of an occupancy status of a vehicle seat

• US 7,113,856 B2
• Filed: 07/20/2002
• Issued: 09/26/2006
• Est. Priority Date: 08/17/2001
• Status: Expired due to Fees

• Current Assignee: IEE International Electronics & Engineering SA (Aerospace Hi-Tech Holding Group Company Limited)
• Original Assignee: IEE International Electronics & Engineering SA (Aerospace Hi-Tech Holding Group Company Limited)
• Inventors: Di Mario Cola, Patrick, Theiss, Christian, Schifflers, Marc
• Primary Examiner(s): NGUYEN, CUONG H
• Application Number:
  US10/487,045
• Publication Number:
  US 20040231906A1
• Time in Patent Office: 1,529 Days
• Field of Search: 701 45- 46, 280/730.1, 280/727, 180/271, 180/273, 307/10.01, 702/127, 340/436, 340/438
• US Class Current: 701/45
• CPC Class Codes: B60R 21/01516 using force or pressure sensing means

Abstract

A method for classifying an occupancy status of a vehicle seat includes associating a filtered class to a specific seat occupancy status based on a plurality of successive readings of at least one parameter value of a seat occupancy sensor, including the steps of: 1) determining an actual value of a first parameter of the seat sensor and associating an actual class to the actual value of the first parameter; 2) storing the actual class in a buffer, and deleting the oldest stored class; 3) plotting a confidence parameter indicative of the reliability of the actual class; 4) setting an updated filtered class to equal (i) an average of the classes stored in the buffer, if the confidence parameter is smaller than a first confidence threshold value, or (ii) the previously determined filter class, if the confidence parameter is greater than or equal to the first confidence threshold value.

Claims

1. A method for the classification of an occupancy status of a vehicle seat, wherein a filtered class is associated to a specific seat occupancy status based on a plurality of successive readings of at least one parameter value of a seat occupancy sensor, said method comprising the steps of:

a. determining an actual value of a first parameter of said seat occupancy sensor and associating an actual class to said actual value of said first parameter,

b. storing said actual class in a buffer comprising several previously determined classes;

c. plotting a confidence parameter, said confidence parameter being indicative of the reliability of the actual class; and

d. setting said filtered class to equal

i) an average of the classes stored in said buffer, if said confidence parameter is smaller than a first confidence threshold value; and

ii) a previously determined filtered class, if said confidence parameter is greater than said first confidence threshold value.

2. The method according to claims 1, wherein in said step d., said updated filtered class is set to equal said previously determined filtered class, if said confidence parameter is equal to said first confidence threshold value.

3. The method according to claim 1, wherein said confidence parameter is decreased if said actual class differs from a previously determined filtered class.

4. The method according to claim 1, wherein said confidence parameter is increased if said actual class corresponds to said previously determined filtered class.

5. The method according to claim 1, further comprising the step of determining an actual value of a second parameter of said seat occupancy sensor, said second parameter being indicative of the quality of the first parameter, and if said second parameter is smaller than a predetermined quality threshold value,

a. increasing said confidence parameter, if said confidence parameter is smaller than said first confidence threshold, and

b. decreasing said confidence parameter, if said confidence parameter is greater than said first confidence threshold.

6. The method according to claim 5, wherein, if said second parameter is greater than said predetermined quality threshold value, said confidence parameter is increased if said actual class corresponds to said previously determined filtered class.

7. The method according to claim 1, further comprising the step of setting a first flag if a parameter value of said seat occupancy sensor indicates a non-human occupancy and, if said first flag is set,

a. increasing said confidence parameter, if said confidence parameter is smaller than a second confidence threshold value, said second threshold value being greater than said first threshold value, and

b. decreasing said confidence parameter, if said confidence parameter is greater than said second confidence threshold.

8. The method according to claim 1, further comprising the step of setting a second flag if a parameter value of said seat occupancy sensor indicates that said occupancy partially occurs outside an active sensor area, and, if said second flag is set, decreasing said confidence parameter if said confidence parameter is greater than said second confidence threshold.

9. The method according to claim 1, wherein said first parameter is indicative of the weight of a passenger or an object occupying said seat.

10. The method according to claim 1, wherein said first parameter is indicative of the width of the contact surface of a passenger or an object occupying said seat.

11. The method according to claim 1, further comprising the step of setting a third flag indicative of an occupancy of the seat, wherein said steps a. to d. are executed only if said third flag is set.

12. A Method for the classification of an occupancy status of a vehicle seat, wherein a filtered class is associated to a specific seat occupancy status based on a plurality of successive readings of at least one parameter value of a seat occupancy sensor, said method comprising the steps of:

a. determining an actual value of a first parameter of said seat occupancy sensor and associating an actual class to said actual value of said first parameter,

b. storing said actual class in a buffer comprising several previously determined classes;

c. plotting a confidence parameter, said confidence parameter being indicative of the reliability of the actual class; and

d. setting an updated filtered class to equal

i) an average of the classes stored in said buffer, if said confidence parameter is smaller than a first confidence threshold value;

or

ii) a previously determined filtered class, if said confidence parameter is greater than said first confidence threshold value.

13. The method according to claim 12, wherein in said step d., said updated filtered class is set to equal said previously determined filtered class, if said confidence parameter is equal to said first confidence threshold value.

14. The method according to claim 12, wherein said confidence parameter is decreased if said actual class differs from a previously determined filtered class.

15. The method according to claim 12, wherein said confidence parameter is increased if said actual class corresponds to said previously determined filtered class.

16. The method according to claim 12, further comprising the step of determining an actual value of a second parameter of said seat occupancy sensor, said second parameter being indicative of the quality of the first parameter, and, if said second parameter is smaller than a predetermined quality threshold value,

a. increasing said confidence parameter, if said confidence parameter is smaller than said first confidence threshold, and

b. decreasing said confidence parameter, if said confidence parameter is greater than said first confidence threshold.

17. The method according to claim 16, wherein, if said second parameter is greater than said predetermined quality threshold value, said confidence parameter is increased if said actual class corresponds to said previously determined filtered class.

18. The method according to claim 12, further comprising the step of setting a first flag if a parameter value of said seat occupancy sensor indicates a non-human occupancy and, if said first flag is set,

a. increasing said confidence parameter, if said confidence parameter is smaller than a second confidence threshold value, said second threshold value being greater than said first threshold value, and

b. decreasing said confidence parameter, if said confidence parameter is greater than said second confidence threshold.

19. The method according to claim 12, further comprising the step of setting a second flag if a parameter value of said seat occupancy sensor indicates that said occupancy partially occurs outside an active sensor area, and, if said second flag is set, decreasing said confidence parameter if said confidence parameter is greater than said second confidence threshold.

20. The method according to claim 12, wherein said first parameter is indicative of the weight of a passenger or an object occupying said seat.

21. The method according to claim 12, wherein said first parameter is indicative of the width of the contact surface of a passenger or an object occupying said seat.

22. The method according to claim 12, further comprising the step of setting a third flag indicative of an occupancy of the seat, wherein said steps a. to d. are executed only if said third flag is set.