Occupant type and position detection system

• US 6,005,958 A
• Filed: 04/23/1997
• Issued: 12/21/1999
• Est. Priority Date: 04/23/1997
• Status: Expired due to Term

• Current Assignee: Automotive Systems Laboratory, Incorporated (Ningbo Junsheng Investment Group Co., Ltd.)
• Original Assignee: Automotive Systems Laboratory, Incorporated (Ningbo Junsheng Investment Group Co., Ltd.)
• Inventors: Farmer, Michael E., Bruce, Michael P.
• Primary Examiner(s): Bella, Matthew C.
• Application Number:
  US08/841,521
• Time in Patent Office: 972 Days
• Field of Search: 382/103, 382/104, 382/106, 701/45, 280/735, 340/438
• US Class Current: 382/103
• 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: B60N 2/28 Seats readily mountable on, and dismountable from, existing seats or other parts of the vehicle
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A method and system (10) for detecting vehicle occupant type and position utilizes a single camera unit (12) positioned, for example at the driver or passenger side A-pillar, to generate image data of the front seating area of the vehicle. The present invention distinguishes between objects, forwardly or rearwardly facing child seats, and occupants, by periodically mapping the image taken of the interior of the vehicle into an image profile (104), and utilizing image profile matching with stored profile data (110) to determine the occupant or object type. The system and method of the present invention track occupant type and position in both parallel and perpendicular directions relative to a fixed structure such as the vehicle instrument panel to optimize both the efficiency and safety in controlling deployment of a occupant safety device, such as an air bag (28).

Claims

1. A system for determining vehicle occupant type and position relative to a fixed structure within the vehicle comprising:

an imaging means mounted at a single location within the vehicle interior and having a predetermined field of view so that front driver side seat and a front passenger side seat are both simultaneously viewable by said imaging means but not simultaneously in focus, wherein said imaging means generates an output signal representative of an instantaneous position of any object located within the field of view;

a narrow depth of focus lens operatively coupled to said imaging means, wherein said narrow depth of focus lens has an optic axis;

a de-blurring filter, wherein said de-blurring filter cooperates with said narrow depth of focus lens to provide a measure of distance along said optic axis to said object within the field of view relative to the fixed structure of the vehicle;

a memory for storing predetermined object profile data characteristic of a plurality of different types of objects when situation in either front seat of the vehicle; and

a processor means operatively coupled to said de-blurring filter for identifying the type of object located in the front seats of the vehicle by comparing said imaging means output signal to said predetermined object profile data.

2. The system of claim 1 wherein said processor means comprises means for determining the distance between an object located within the field of view and the fixed structure within the vehicle based on said imaging means output signal.

3. The system of claim 2 further comprising means for optimizing deployment of a passenger safety restraint based on the identified type of object and distance.

4. The system of claim 3 further comprising means for storing instantaneous distance measurements, and means for tracking changes in the instantaneous distance measurements, wherein said means for optimizing safety restraint deployment comprises means for predicting a vehicle crash based on said tracked changes in distance.

5. The system of claim 1 wherein said single location comprises a vehicle A-pillar, and wherein said imaging means further comprises a perspective angle correction lens for translating the predetermined field of view from a perspective view to a two-dimensional view.

6. The system of claim 1 further comprising means for optimizing deployment of a passenger safety restraint based on the identified type of object.

7. The system of claim 1 wherein said processor means is responsive to said measure of distance along said optic axis to said object within the field of view relative to the fixed structure of the vehicle.

8. A system for determining vehicle occupant type and position relative to a fixed structure within the vehicle comprising:

an imaging means mounted at a single location within the vehicle interior and having a predetermined field of view so that a front driver side seat and a front passenger side seat are both simultaneously viewable by said imaging means, wherein said imaging means generates an output signal representative of an instantaneous position of any object located within the field of view;

a memory for storing predetermined object profile data characteristic of a plurality of different types of objects when situated in either front seat of the vehicle;

a processor mans for identifying the type of object located in the front seats of the vehicle by comparing said imaging means output signal to said predetermined object profile data, said processor means comprising means for determining the distance between an object located within the field of view and the fixed structure within the vehicle based on said imaging means output signal;

means for generating two-dimensional image data representative of any objects located within the predetermined field of view; and

means for generating a two-dimensional range grid which vertically divides the field of view into a plurality of independent regions each representative of a predetermined size of vehicle interior space, wherein said grid if oriented so that the fixed vehicle structure is located proximate with one end region, and the vehicle front seats are located proximate with the opposite end region, wherein said means for determining distance comprises means for comparing said generated two-dimensional image data with said range grid to detect which if any of the plurality of regions are occupied by an object.

9. The system of claim 8 wherein said imaging means comprises a lens element, and said means for generating a two-dimensional range grid comprises a grid pattern etched on the surface of said lens element.

10. The system of claim 9 wherein said imaging means further comprises means for transmitting light into the predetermined field of view, and said means for generating a two-dimensional range grid further comprises a grid pattern etched onto said light transmitting means which matches said grid pattern etched onto said lens element.

11. The system of claim 8 wherein said imaging means comprises a CCD element, and said means for generating a two-dimensional range grid comprises a grid printed on said CCD element.

12. The system of claim 11 wherein said imaging means further comprises means for transmitting light into the predetermined field of view, and said means for generating a two-dimensional range grid further comprises a grid pattern etched onto said light transmitting means which matches said grid pattern et etched onto said CCD element.

13. The system of claim 8 further comprising a narrow depth of focus lens coupled to said imaging means and a de-blurring filter coupled to said processor means, wherein the front driver side seat and the front passenger side seat are not simultaneously in focus by said imaging means, said means for determining the distance is responsive to said narrow depth of focus lens, said de-blurring filter, and said two-dimensional grid for estimating the absolute distance based on the lateral location of the object within the field of view relative to the fixed structure of the vehicle.

14. The system of claim 8 wherein said means for generating two-dimensional image data comprises a processor having a deblurring algorithm.

15. The system of claim 8 further comprising means for optimizing deployment of a passenger safety restraint based on the identified type of object and distance.

16. The system of claim 15 further comprising means for storing instantaneous distance measurements, and means for tracking changes in the instantaneous distance measurements, wherein said means for optimizing safety restraint deployment comprises means for predicting a vehicle crash based on said tracked changes in distance.

17. The system of claim 8 wherein said single location comprises a vehicle A-pillar, and wherein said imaging means further comprises a perspective angle correction lens for translating the predetermined field of view from a perspective view to a two-dimensional view.

18. The system of claim 8 further comprising means for optimizing deployment of a passenger safety restraint based on the identified type of object.

19. A method for determining position of an object located in a vehicle relative to a fixed structure within the vehicle comprising the steps of:

generating two-dimensional image data representative of any objects located within a front seating area of the vehicle;

generating a two-dimensional range grid by vertically dividing the front seating area into a plurality of independent regions each representative of predetermined size of vehicle interior, wherein the fixed vehicle structure is located proximate with one end region, and the vehicle front seats are located proximate with the opposite end region;

detecting lateral location of the object relative to a narrow depth of focus reference plane using a de-blurring filter; and

estimating the distance between the object and said fixed structure by comparing said generated image data with said range grid and detected lateral location to determine which if any of the plurality of regions are occupied by an object.

20. The method of claim 19 wherein said step of generating a two-dimensional range grid comprises etching said grid onto the surface of a lens element used to generate said two-dimensional image data.

21. The method of claim 19 wherein said step of generating a two-dimensional range grid comprises the step of printing said grid on a CCD element used to generate said two-dimensional image data.

22. The method of claim 19 wherein said step of generating a two-dimensional range grid comprises etching matching grid patterns onto each of a light transmitting and receiving component used to generate said two-dimensional image data, and further comprising the step of estimating a profile of any object located within the front area by detecting warping of the transmitted light grid relative to the receiving light grid.

23. The method of claim 19 further comprising the steps of:

storing predetermined object profile data characteristic of a plurality of different types of objects when situated in either front seat of the vehicle; and

identifying the type of object located in the front seats of the vehicle by comparing said two-dimensional image data to said predetermined object profile data.

24. The method of claim 23 further comprising the step of optimizing deployment of a passenger safety restraint based on the identified type of object and distance.

25. The method of claim 24 further comprising the steps of storing instantaneous distance measurements, and tracking changes in the instantaneous distance measurements, wherein said optimizing step comprises the step of predicting a vehicle crash based on said tracked changes in distance.

26. The method of claim 19 wherein said step of generating two-dimensional image data comprises the step of positioning an imaging system having a predetermined field of view at a single location within the vehicle.

27. The method of claim 26 wherein said single location comprises a vehicle A-pillar, and wherein said step of generating two-dimensional image data further comprises the step of translating the predetermined field of view from a perspective view to a two-dimensional view.

28. A method for determining position of an object located in a vehicle relative to a fixed structure within the vehicle comprising the steps of:

generating two-dimensional image data representative of any objects located within a front seating area of the vehicle;

generating a two-dimensional range grid by vertically dividing the front seating area into a plurality of independent regions each representative of predetermined size of vehicle interior, wherein the fixed vehicle structure is located proximate with one end region, and the vehicle front seats are located proximate with the opposite end region; and

estimating the distance between the object and said fixed structure by comparing said generated image data with said range grid to determine which if any of the plurality of regions are occupied by an object.