Method and device for detecting the occupancy state of a seat

• US 7,492,923 B2
• Filed: 02/24/2003
• Issued: 02/17/2009
• Est. Priority Date: 08/21/2002
• Status: Expired due to Fees

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Freienstein, Heiko, Trinh, Hoang, Bothe, Hans-Dieter, Engelberg, Thomas
• Primary Examiner(s): Wu; Jingge
• Assistant Examiner(s): Bitar; Nancy
• Application Number:
  US10/524,703
• Publication Number:
  US 20060161321A1
• Time in Patent Office: 2,185 Days
• Field of Search: 701/45, 701/140, 701/195, 701/203, 701/205, 382/190, 382/100, 382/103, 382/320, 382/106, 382/175, 382/199, 340/573.1, 348/77, 250/221, 280/733, 280/735
• US Class Current: 382/104
• CPC Class Codes: B60N 2/002 Seats provided with an occupancy detection means mounted therein or thereon detection means responsive to presence or absence of children B60N2/266
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays
• CPC Class Codes: B60R 21/01556 Child-seat detection systems

Abstract

A method and a device for detecting the occupancy state of a seat, e.g., in a vehicle, and for use in activating a restraint mechanism allocated to the seat, as a function of the occupancy state, are provided. With the aid of an image recording system, a 3D image of the seat is recorded and evaluated with respect to the occupancy state, and optionally also with respect to the type of the occupancy. For the evaluation, a 3D pattern is drawn upon, which is available externally or which is able to be generated internally in an initialization step. A hierarchically constructed evaluation also permits, after determination of an occupancy state, a classification with respect to the type of the respective occupancy.

Claims

1. A method for detecting an occupancy state of a seat in a vehicle, comprising:

recording a 3D image of the seat using an image recording system;

obtaining a 3D pattern of the seat;

evaluating the 3D image of the seat with respect to at least one of the occupancy state of the seat and an occupancy type of the seat, wherein the evaluation includes consideration of the 3D pattern of the seat, and wherein if a deviation between the 3D image and the 3D pattern exceeds a predetermined minimum value for the evaluation, a determination of the occupancy state is made indicating that the seat is occupied, and wherein the determination of the occupancy state is regarded as conclusive only if substantially identical evaluation result is obtained over a plurality of sequential time points; and

activating a restraint mechanism associated with the seat, as a function of at least one of the occupancy state of the seat and the occupancy type of the seat.

2. The method as recited in claim 1, wherein the 3D pattern of the seat is subdivided into partial regions of the seat, and the evaluation of the 3D image includes evaluation of the partial regions of the 3D pattern of the seat.

3. The method as recited in claim 2, wherein the evaluation of the partial regions of the 3D pattern includes evaluation of mutual relationships of the partial regions with one another.

4. The method as recited in claim 1, wherein the 3D pattern of the seat is a wire screen model representing an approximation of the real shape of the seat.

5. The method as recited in claim 1, wherein the 3D pattern of the seat is derived from seat manufacturer'"'"'s specification of the seat.

6. The method as recited in claim 1, wherein the 3D pattern of the seat is derived in an initialization step from a 3D image of the seat in an unoccupied state under specified surrounding conditions.

7. The method as recited in claim 2, wherein, based on a comparison between a predetermined minimum value and a deviation between at least one selected partial region of the 3D pattern and a corresponding partial region of the 3D image, a type of at least one of an object and a person occupying the seat is determined.

8. The method as recited in claim 7, wherein predetermined parameters of the at least one of the object and the person are further determined.

9. The method as recited in claim 1, wherein, for the determination of the occupancy state, a temporal filtering is performed, including ascertaining one of a moving average and a median value of the deviation.

10. The method as recited in claim 1, wherein, for the evaluation, at least one of measured data corresponding to the 3D image and data corresponding to the 3D pattern are transformed to provide a uniform data format for the 3D image and the 3D pattern.

11. A device for determining an occupancy state of a seat in a vehicle, the occupancy state being considered in the activation of a restraint mechanism associated with the seat, the device comprising:

an image recording system for recording a 3D image of the seat; and

an evaluation circuit for evaluating the 3D image of the seat with respect to at least one of the occupancy state of the seat and an occupancy type of the seat, wherein the evaluation includes comparing a 3D pattern of the seat to the recorded 3D image of the seat, and wherein if a deviation between the 3D image and the 3D pattern exceeds a predetermined minimum value for the evaluation, a determination of the occupancy state is made indicating that the seat is occupied, and wherein the evaluation circuit includes a filter circuit for temporal filtering of a plurality of evaluation results sequentially obtained over time, and wherein the determination of the occupancy state is regarded as conclusive only if substantially identical evaluation result is obtained over a plurality of sequential time points.

12. The device as recited in claim 11, wherein the 3D pattern of the seat is subdivided into partial regions of the seat, and the evaluation of the 3D image includes evaluation of the partial regions of the 3D pattern of the seat.

13. The device as recited in claim 11, further comprising a memory associated with the evaluation circuit for storing data for the 3D pattern, wherein the 3D pattern is in the form of a wire screen model.

14. The device as recited in claim 13, wherein the 3D pattern data is obtained from an external source.

15. The device as recited in claim 13, wherein the 3D pattern data are derived in an initialization step from 3D image data of an unoccupied seat under predefined surrounding conditions.