Confidence boost for automotive occupant classifications

• US 7,623,950 B2
• Filed: 06/09/2005
• Issued: 11/24/2009
• Est. Priority Date: 06/09/2005
• Status: Active Grant

• Current Assignee: Aptiv Technologies AG
• Original Assignee: Delphi Technologies, Inc. (BorgWarner Incorporated)
• Inventors: Kong, Hongzhi, Bauson, William A., Sun, Qin
• Primary Examiner(s): Camby; Richard M.
• Application Number:
  US11/149,816
• Publication Number:
  US 20060282201A1
• Time in Patent Office: 1,629 Days
• Field of Search: 701/1, 701/45, 701/36, 701/47, 280/735, 180/271, 180/282, 180/274
• US Class Current: 701/45
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays

Abstract

The present invention relates to systems for determining the position and the type of an occupant in a vehicle. More specifically, the present invention provides an occupant position and type classification system including an occupant detection module, a processor in communication with the occupant detection module, and memory accessible by the processor and storing program instructions executable by the processor to perform the steps of categorizing the occupant into one of a plurality of static categories, each of the static categories including at least one class indicative of the occupant'"'"'s type or position in the vehicle, and classifying the occupant into one of the classes.

Claims

1. A method of classifying an occupant of a motor vehicle, said method comprising the steps of:

processing a plurality of image frames to detect an occupant;

categorizing the occupant into one of a plurality of static categories, each of the static categories including at least one class indicative of at least one of an occupant type and a position in the vehicle; and

classifying the occupant into the at least one class, wherein the step of classifying includes determining a spatial confidence having a consistency over a predetermined period of time, and observing the consistency of the spatial confidence over the predetermined period of time to establish a temporal confidence.

2. The method of claim 1 wherein the at least one class is dynamic.

3. The method of claim 1 further comprising a step of defining a confidence condition, the confidence condition indicating a desired accuracy in the classification of the occupant into the at least one class.

4. The method of claim 3 wherein the step of classifying includes a step of achieving the confidence condition.

5. The method of claim 4 wherein the step of classifying includes a step of locking the one of the plurality of static categories when the confidence condition has been achieved.

6. The method of claim 5 wherein the step of classifying includes a step of limiting the classification of the occupant to the locked one of the plurality of static categories.

7. The method of claim 3 further comprising a step of utilizing the spatial confidence and the temporal confidence to boost the desired accuracy.

8. An occupant position classification system, said system comprising:

means for capturing a plural of image frames;

a processor in communication with said means for capturing the image frames; and

memory accessible by said processor and storing program instructions executable by said processor to perform method steps, the method steps comprising;

processing the plurality of image frames to detect an occupant;

categorizing the occupant into one of a plurality of static categories, each of the static categories including at least one class indicative of at least one of an occupant type and a position in the vehicle;

classifying the occupant into the at least one class;

determining a spatial confidence distribution pattern of each of the plurality of image frames; and

determining a temporal distribution pattern of each of the plurality of image frames over a predetermined number of consecutive image frames, wherein the program instructions are executable by said processor to perform a step of defining a confidence condition, the confidence condition indicating a desired accuracy in the classification of the occupant into the at least one class.

9. The occupant position classification system of claim 8 wherein the program instructions are executable by said processor such that said step of classifying includes a step of achieving the confidence condition.

10. The occupant position classification system of claim 9 wherein the program instructions are executable by said processor such that said step of classifying includes a step of locking the one of the plurality of static categories when the confidence condition has been achieved.

11. The occupant position classification system of claim 10 wherein the program instructions are executable by said processor such that said step of classifying includes a step of limiting the classification of the occupant to the locked one of the plurality of static categories.

12. The occupant position classification system of claim 8 wherein the program instructions are executable by said processor to perform a step of utilizing the spatial confidence distribution pattern and the temporal distribution pattern to boost the desired accuracy.