Method and device for detecting an object in a vehicle in particular for occupant protection systems

• US 7,376,248 B2
• Filed: 12/12/2001
• Issued: 05/20/2008
• Est. Priority Date: 12/20/2000
• Status: Expired due to Fees

• Current Assignee: Continental Automotive GmbH (Continental AG)
• Original Assignee: Siemens AG
• Inventors: Ertl, Ludwig, Kohler, Thorsten
• Primary Examiner(s): Bella; Matthew C.
• Assistant Examiner(s): WANG, CLAIRE X
• Application Number:
  US10/451,100
• Publication Number:
  US 20040040772A1
• Time in Patent Office: 2,351 Days
• Field of Search: 382/190, 382/100, 382/103, 382/104, 382/106, 382/154
• US Class Current: 382/104
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays

Abstract

In optical image processing methods for determining the occupation of a vehicle seat, it is advantageous to know the position of the vehicle seat (14), even in the case when said seat is occupied. The above is achieved, whereby the side surface of the backrest (11), facing the camera (30) is part of a boundary plane. A section (T, B), between a separating plane, cutting vertically through the vehicle seat and the boundary plane (B) is at least partly not covered by a seat occupant in the direction of the camera. By means of an image processing method the position of the seat may be determined.

Claims

1. A method for detecting a position of a backrest of a vehicle seat, comprising:

registering a 3D image area in an interior of the vehicle by a camera;

transmitting image information registered by the camera to an evaluation unit;

with the evaluation unit, selecting a specified section from the image area, the specified section located between a separating plane and a boundary plane, the separating plane and the boundary plane defined such that at least part of the specified section is at most partially obscured by an object, the boundary plane including and/or touching an edge of the backrest facing the camera, the boundary plane running parallel to a side surface of the backrest, the separating plane vertically transecting the vehicle seat and being parallel to the boundary plane;

determining the position of the backrest from the image information registered in the specified section.

2. The method according to claim 1, wherein the boundary plane is substantially supported by a z-axis and a x-axis of a vehicle coordinate system, and a position of the boundary plane in a y direction is dependent on a mounting position of the vehicle seat in the y direction.

3. The method according to claim 2, wherein the separating plane is substantially supported by the z-axis and the x-axis of the vehicle coordinate system, and the separating plane is located in the y direction between a headrest of the vehicle seat and the boundary plane.

4. The method according to claim 1, wherein the specified section encompasses an area that includes a side surface of the headrest that faces the camera.

5. The method according to claim 1, wherein:

p1 a distance image with image points is produced from the image information, the image is transformed into a Cartesian system of coordinates having a fixed vehicle reference, the Cartesian system of coordinates has a coordinate axis pointing into a longitudinal axis of the vehicle, the Cartesian system of coordinates has a coordinate axis pointing at right angles to the longitudinal axis of the vehicle, and the Cartesian system of coordinates has a coordinate axis pointing vertically; and

the specified section is subdivided into volume pixel elements, an initial specified value is assigned to a first group of the volume pixel elements in which no image points of the backrest were registered and at least a further specified value is assigned to a second group of the volume pixel elements in which at least one image point of the backrest was registered.

6. The method according to claim 5, wherein values assigned to the volume pixel elements are compared with at least one specified volume pixel element pattern.

7. The method according to claim 5, wherein:

the volume pixel elements are formed as a rectangular solid or cube with a specified edge length between approximately 2 and 4 cm, which border each other directly without overlapping; and

surfaces of the volume pixel elements are in each case formed parallel to the coordinate axes of the Cartesian system of coordinates.

8. The method according to claim 5, wherein:

the separating plane is substantially supported by a z-axis and a x-axis of the Cartesian system of coordinates, and the separating plane is located in a y direction between a headrest of the vehicle seat and the boundary plane; and

the specified section is subdivided in the y direction into 3 and 5 volume pixel element planes, a third group of the volume pixel elements in the volume pixel element planes that are assigned to another specified value are projected into an evaluation plane, the evaluation plane registers the third group of the volume pixel elements for further evaluation, the third group of volume pixel elements lying within an adjustment range of the backrest of the vehicle.

9. The method according to claim 8, wherein the evaluation plane registers volume pixel elements that have values which have remained unchanged at least a specified number of times, during a specified period of lapsed time.

10. The method according to claim 1, wherein the backrest is moveable in relation to the vehicle.

11. The method according to claim 1, which comprises:

determining a surface shape and/or a position of the backrest using specified geometric dimensions of the backrest; and

determining a volume distribution of an object in front of the backrest by using optical detection methods.

12. The method according to claim 1, which comprises:

determining a position of a starting point of the backrest corresponding to a position of a volume pixel element in an evaluation plane located closest to the camera and a vehicle roof, the volume pixel element provided with a value.

13. The method according to claim 12, which comprises:

taking a mean of several measurements of the position of the starting point.

14. The method according to claim 12, which comprises:

from the position of the starting point, taking at least an approximate mean of at least one item selected from a group consisting of an inclination of the backrest, a height position of the vehicle seat, and an adjustment position of the vehicle seat along a seat position track; and

after taking the mean, calculating at least one surface shape or surface position of a component selected from a group consisting of the vehicle seat, the backrest, a seat base and a headrest.

15. The method according to claim 1, which comprises:

determining a position of a component selected from a group consisting of a vehicle seat, a seat base, the backrest, a headrest, a window frame, an adjustable window pane, and a vehicle mirror.

16. The method according to claim 1, which comprises:

determining a position of an object selected from a group consisting of a vehicle occupant, a portion of the vehicle occupant, a child car seat, and an item on the vehicle seat.

17. The method according to claim 1, wherein a further boundary plane is specified by a y position of a side surface of a headrest facing the camera, a further separating plane vertically transects the headrest, and a position of the headrest is determined from volume pixel elements that have been provided with an additional value that are located between the further boundary plane and the further separating plane.

18. The method according to claim 1, which comprises:

using multiple volume pixel elements, which have been provided with an additional value, of an evaluation plane to register the backrest or a headrest, and using the multiple volume pixel elements to determine a virtual straight line crossing a plane of a seat positioning track in a position point used for determining an overall position of a vehicle seat along the seat positioning track.

19. The method according to claim 1, which comprises:

determining the position of the backrest from a preceding measuring cycle; and

if the position of the backrest cannot be determined from the preceding measuring cycle, applying an angle of inclination of 105°

to 110°

to the backrest.

20. The method according to claim 1, which comprises:

using a seat position sensor to measure a position of the vehicle seat.

21. The method according to claim 1, which comprises:

using a weight sensor to determine a weight or a weight distribution of an object located on the vehicle seat.

22. The method according to claim 1, which comprises:

using at least one switch for supplying information about a change in at least one seat position parameter selected from a group consisting of a seat height, an angle of inclination of the backrest, and a seat position along a seat positioning track;

the switch attached to a mechanical and/or electrical seat adjustment device.

23. The method according to claim 1, which comprises:

comparing information in an evaluation plane with a grayscale image registered by the camera.

24. The method according to claim 1, which comprises:

determining a surface shape of the vehicle seat when the vehicle seat is occupied.

25. The method according to claim 1, wherein:

the specified section encompasses a bounded area that is bounded by two planes;

the bounded area includes a top edge of a window frame that supports a window pane, the top edge of the window frame faces the camera;

the top edge of the window pane is optically registered by the camera; and

a closing motion of the window pane is dependent on a position of a vehicle occupant and on a position of the top edge of the window pane.

26. The method according to claim 1, wherein a position of a side surface, which faces the camera, of the vehicle seat is determined by a position of the vehicle seat in a y-direction, and the position of the side surface of the vehicle seat remains substantially constant when the vehicle seat is moved in the y direction.

27. The method according to claim 1, wherein the image information registered by the camera is image data, the image data is transmitted by the camera to the evaluation unit, and the image data is processed in the evaluation unit.

28. The method according to claim 27, wherein the camera is implemented as a 3D camera for registering stereo images and includes two image sensors.

29. The method according to claim 27, wherein the camera has an aperture angle of approximately 100×

90 degrees.