Methods and apparatus for classification of occupancy using wavelet transforms

• US 20080059027A1
• Filed: 08/31/2006
• Published: 03/06/2008
• Est. Priority Date: 08/31/2006
• Status: Abandoned Application

• Current Assignee: Eaton Corp. (Wisconsin) (Eaton Corporation PLC.)
• Original Assignee: Eaton Corp. (Wisconsin) (Eaton Corporation PLC.)
• Inventors: Farmer, Michael E., Bapna, Shweta R.
• Application Number:
  US11/514,299
• Publication Number:
  US 20080059027A1
• Time in Patent Office: Days
• US Class Current: 701/45
• CPC Class Codes: B60R 21/01538 for image processing, e.g. cameras or sensor arrays

Abstract

Improved methods and apparatus for classifying occupancy of a position use wavelet transforms, such as Gabor filters, for processing images obtained in conjunction therewith. For example, a computer system comprises an algorithm that utilizes a wavelet transform for processing of imagery associated with a position in order to classify occupancy of that position. A method comprises steps of: obtaining an image of the position; optionally segmenting the image at the position; optionally dividing the image into multiple key regions for further analysis; analyzing texture of the image using one or more wavelet transforms; and classifying occupancy of the position based on the texture of the image.

Claims

1. A computer system comprising an algorithm for processing of imagery associated with a position to be analyzed, wherein the imagery is processed to classify occupancy of that position, and wherein the algorithm utilizes a wavelet transform in processing of the imagery.

2. The computer system of claim 1, wherein the algorithm uses spatial filtering for processing of the imagery.

3. The computer system of claim 1, wherein the wavelet transform comprises at least one Gabor filter.

4. The computer system of claim 1, wherein the position is classified as being empty or occupied as a result of processing the imagery.

5. The computer system of claim 1, wherein processing of the imagery comprises using statistical analysis of feature vectors derived from the wavelet transform.

6. The computer system of claim 5, wherein the statistical analysis comprises use of histograms, wherein histograms associated with classification of the position as empty are narrow and focused as compared to histograms being associated with classification of the position as occupied, which are broader and more uniformly distributed.

7. The computer system of claim 1, wherein the position comprises a vehicle seat.

8. An automated safety system comprising a computer system, wherein the computer system comprises:

an algorithm for processing of imagery associated with a position to be analyzed, wherein the imagery is processed to classify occupancy of that position, and

wherein the algorithm utilizes a wavelet transform in processing of the imagery.

9. The automated safety system of claim 8, wherein the system comprises an airbag deployment system.

10. The automated safety system of claim 8, comprising image-based sensing equipment.

11. The automated safety system of claim 8, comprising an electronic control unit for selective deployment of safety equipment.

12. The automated safety system of claim 11, wherein the safety equipment comprises an airbag.

13. A method for classification of occupancy at a position, the method comprising steps of:

obtaining an image of the position for use in classification of the occupancy at that position;

optionally segmenting the image at the position;

optionally dividing the image into multiple key regions for further analysis;

analyzing texture of the image using one or more wavelet transforms; and

classifying occupancy of the position based on the texture of the image.

14. The method of claim 13, wherein the step of analyzing texture of the image comprises using a bank of Gabor filters.

15. The method of claim 13, wherein Gabor filter coefficients from the bank of Gabor filters are used to form a feature vector.

16. The method of claim 15, wherein statistical analysis is performed on the feature vector.

17. The method of claim 16, wherein the statistical analysis comprises use of histograms, wherein histograms associated with classification of the position as empty are narrow and focused as compared to those histograms associated with classification of the position as occupied, which are broader and more uniformly distributed.

18. The method of claim 13, further comprising transmitting information associated with the classification to an electronic control unit.

19. The method of claim 18, wherein the electronic control unit comprises an airbag controller.

20. The method of claim 13, wherein the position is a seat within a vehicle.

21. The method of claim 13, wherein the occupancy of the position is assigned a classification of “

empty”

or “

occupied.”