Method for controlling output of a classification algorithm

• US 8,054,193 B1
• Filed: 04/27/2009
• Issued: 11/08/2011
• Est. Priority Date: 08/26/2002
• Status: Expired due to Fees

• Current Assignee: American Vehicular Sciences LLC (Acacia Research Corporation)
• Original Assignee: Automotive Technologies International Incorporated
• Inventors: Chen, Tie-Qi, Piirainen, Ray, Breed, David S.
• Primary Examiner(s): Swarthout; Brent
• Application Number:
  US12/430,417
• Time in Patent Office: 925 Days
• Field of Search: 340/436, 340/438, 280/735, 280/801.1, 701/45
• US Class Current: 340/667
• CPC Class Codes: B60R 21/01516 using force or pressure sensing means
• CPC Class Codes: B60R 21/0153 using field detection presence sensors

Abstract

Method for controlling output of a classification algorithm which classifies an occupant of a seat in a vehicle in which a bladder or other type of weight sensor is arranged in a bottom cushion of the seat, data relating to the pressure exerted by the occupant on the bottom cushion is obtained from the weight sensor, the occupant is initially classified, a current classification is output using data from the weight sensor, the occupant is periodically re-classified using data from the weight sensor, and a classification change is allowed only upon obtaining evidence of a new classification which is greater than evidence of the current classification. The classification change may be enabled by determining a substantially consecutive period of time when the re-classification is unchanged and different from the current classification, and enabling the classification change upon when the consecutive period of time is greater than a threshold.

Claims

1. A method for controlling output of a classification algorithm embodied in computer-readable media which classifies an occupant of a seat in a vehicle, comprising:

obtaining data about the occupant using at least one sensor system;

classifying the occupant based on the obtained data using a processor and outputting from the processor, a current classification of the occupant;

subsequently periodically re-classifying the occupant using the processor;

determining a substantially consecutive period of time that the re-classification of the occupant is the same as the current classification using a timing system;

setting, using the processor, a comparison threshold as the lesser of the period of time that the occupant has been classified or re-classified as the current classification or a predetermined maximum time value;

detecting a change in classification using the processor, and then determining a substantially consecutive period of time that the re-classification of the occupant is the changed classification using the timing system; and

changing the current classification only when the period of time in which the classification is the changed classification is greater than the comparison threshold and outputting the changed classification from the processor.

2. The method of claim 1, wherein the step of obtaining data about the occupant comprises obtaining data about weight of the occupant using the at least one sensor system and the step of classifying the occupant comprises classifying the occupant using the weight data, the occupant being re-classified using the weight data.

3. The method of claim 1, wherein the at least one sensor system includes a spatial sensor system and the step of obtaining data about the occupant comprises arranging the spatial sensor system to generate a field over a bottom cushion of the seat and in which the occupant is expected to be situated and obtaining data about the occupant from the spatial sensor system, the step of classifying the occupant comprising classifying the occupant using data about the occupant from the spatial sensor system, the occupant being re-classified using data about the occupant from the spatial sensor system.

4. The method of claim 1, wherein the at least one sensor system comprises a force or weight sensor that obtains an indication of the force or weight applied to the seat by the occupant.

5. The method of claim 1, wherein the classification of the occupant is performed using a trained neural network embodied in computer-readable media.

6. The method of claim 1, wherein the at least one sensor system comprises a plurality of sensors such that the classification of the occupant is performed using the data obtained from the sensors.

7. The method of claim 6, wherein the plurality of sensors includes at least one sensor selected from a group consisting of a capacitance-based sensor, an electric field-based sensor, a radar or other electromagnetic wave-based sensor, a camera-based sensors including a 3D sensor, and an ultrasonic-based sensor.

8. The method of claim 1, wherein the at least one sensor system comprises at least one camera such that the classification of the occupant is performed using the data obtained from the at least one camera.

9. The method of claim 1, wherein the classification of the occupant is performed using a trained neural network embodied in computer-readable media, a combination neural network embodied in computer-readable media or a modular neural network embodied in computer-readable media.

10. A method for controlling classification of an occupant of a seat, comprising:

obtaining data about occupancy of the seat using at least one sensor system;

setting, using a processor, an output classification to a restraint system disable state, the restraint system disable state including a state wherein the seat is empty;

subsequently classifying occupancy of the seat based on the obtained data using the processor;

determining, using the processor, whether the classification is other than a restraint system disable state and if not, periodically repeating the step;

otherwise, when the classification is other than a restraint system disable state, repeating the classification step;

if the repeated classification step provides a classification of restraint system disable state, setting the output classification to a restraint system disable state, and if not, then setting the output classification to the classification that is other than the restraint system disable state;

repeating the classification step using the processor; and

changing the classification only when the repeated classification step provides a classification of a restraint system disable state in which case, the output classification is changed to a restraint system disable state,

wherein the step of setting the output classification comprises providing a restraint system disable state in which a stored classification is set to a restraint system disable state, the step of classifying occupancy of the seat comprising;

when the classification is other than a restraint system disable state, exiting the restraint system disable state and storing the non-restraint system disable state classification; and

periodically reclassifying occupancy of the seat using the processor and changing the stored classification to the re-classified occupancy when the re-classified occupancy is different than the stored classification;

determining, using the processor, whether the stored classification satisfies a first condition and if so, entering a revoking state;

determining, using the processor, whether the stored classification satisfies a second condition different than the first condition and if so, exiting the revoking state and entering a classified state; and

when in the classified state, outputting the stored classification from the processor.

11. The method of claim 10, further comprising:

when in the classified state, re-classifying the occupancy of the seat; and

preventing change in the stored classification.

12. The method of claim 10, further comprising:

when in the classified state, re-classifying the occupancy of the seat; and

allowing a change in the stored classification only if the re-classified occupancy satisfies a third condition.

13. The method of claim 12, wherein the third condition is a time-based condition more onerous that the second condition and the second condition is a time-based condition more onerous than the first condition.

15. The method of claim 10, wherein the step of obtaining data about the occupancy of the seat comprises obtaining data about weight of an occupant in the seat using the at least one sensor system and the step of classifying the occupancy of the seat comprises classifying the occupancy of the seat using the weight data, the occupancy being re-classified using the weight data.

16. The method of claim 10, wherein the at least one sensor system includes a spatial sensor system and the step of obtaining data about the occupancy of the seat comprises arranging the spatial sensor system to generate a field over a bottom cushion of the seat, the step of classifying the occupancy of the seat comprising classifying the occupancy of the seat using data from the spatial sensor system, the occupancy being re-classified using data from the spatial sensor system.

17. The method of claim 10, wherein the at least one sensor system comprises a force or weight sensor that obtains an indication of the force or weight applied to the seat by the occupant.

18. The method of claim 10, wherein the classification of the occupancy of the seat is performed using a trained neural network embodied in computer-readable media.

19. The method of claim 10, wherein the at least one sensor system comprises a plurality of sensors such that the classification of the occupancy of the seat is performed using the data obtained from the sensors.

20. The method of claim 19, wherein the plurality of sensors includes at least one sensor selected from a group consisting of a capacitance-based sensor, an electric field-based sensor, a radar or other electromagnetic wave-based sensor, a camera-based sensors including a 3D sensor, and an ultrasonic-based sensor.

21. The method of claim 10, wherein the at least one sensor system comprises at least one camera such that the classification of the occupant is performed using the data obtained from the at least one camera.

22. The method of claim 10, wherein the classification of the occupant is performed using a trained neural network embodied in computer-readable media, a combination neural network embodied in computer-readable media or a modular neural network embodied in computer-readable media.

14. A method for controlling output of a classification algorithm which classifies an occupant of a seat in a vehicle, comprising:

arranging a force or weight sensor in connection with the seat;

obtaining data relating to the force or weight exerted by the occupant on a bottom cushion of the seat from the force or weight sensor;

initially classifying the occupant based on the obtained data from the force or weight sensor using a processor and outputting a current classification from the processor;

subsequently periodically re-classifying the occupant based on the data from the force or weight sensor using the processor;

determining a substantially consecutive period of time that the re-classification of the occupant is the same as the current classification using a timing system;

setting, using the processor, a comparison threshold as the lesser of the period of time that the occupant has been classified or re-classified as the current classification or a predetermined maximum time value;

detecting a change in classification and then determining a substantially consecutive period of time that the re-classification of the occupant is the changed classification using the timing system; and

changing the current classification only when the period of time in which the classification is the changed classification is greater than the comparison threshold and outputting the changed classification from the processor.