Enhancement of vehicle interior digital images

• US 20030223617A1
• Filed: 05/28/2002
• Published: 12/04/2003
• Est. Priority Date: 05/28/2002
• Status: Active Grant

• Current Assignee: TRW Inc. (Northrop Grumman Corporation)
• Original Assignee: TRW Inc. (Northrop Grumman Corporation)
• Inventors: Wallace, Jon K., Khairallah, Farid, Dunbridge, Barry, Berenz, John J.
• Granted Patent: US 7,123,747 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: G06F 18/24323 Tree-organised classifiers
• CPC Class Codes: G06T 2207/30268 Vehicle interior
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 5/001 Image restoration
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A method for helping to control a vehicle occupant protection device (22) includes taking an image of the vehicle interior with a digital imager (50) having an array of pixels (53). A contiguous portion of the image less than the entire image is selected. At least one image enhancement technique is applied to the selected image portion. The enhanced image portion is combined with the other portions of the image to make an enhanced image. The enhanced image is analyzed to detect at least one of features and characteristics of the enhanced image. Alternatively, a selected non-contiguous group of the pixels (53) of the imager (50) are read out, as representative of the entire image, to estimate the illumination levels across the entire array of pixels. In one aspect, the imager shutter (56) speed may be controlled to enhance the image.

Claims

1. A method for helping to control a vehicle occupant protection device, said method comprising the steps of:

taking an image of the vehicle interior with a digital imager having an array of pixels;

selecting a contiguous portion of the image that is less than the entire image;

applying at least one image enhancement technique to the selected portion of the image;

combining the enhanced image portion with the other portions of the image to make an enhanced image; and

analyzing the enhanced image to detect at least one of features and characteristics of the enhanced image.

2. A method as set forth in claim 1 wherein said selecting step includes selecting an image portion having an undesired level of brightness and said applying step includes the step of retaking the selected image portion at a different shutter speed to make an enhanced image portion having a different level of brightness.

3. A method as set forth in claim 1 wherein said selecting step includes selecting an image portion having an undesired level of brightness and said applying step includes the step of passing the image through a variable gain amplifier to vary the gain of the amplifier.

4. A method as set forth in claim 3 wherein said step of taking an image includes taking an image with an imager having a first bit range, said analyzing step includes passing the image through an ADC having a second bit range less than the first bit range of the imager, said selecting step includes the step of selecting an image portion having its significant bits in the lower range of the bit range of the ADC, and said applying step includes the step of amplifying the selected image portion to raise the significant bits of the image to a higher portion of the bit range of the ADC.

5. A method as set forth in claim 1 wherein said step of analyzing the enhanced image includes the step of reading out all the pixels of the imager and analyzing the entire image.

6. A method as set forth in claim 1 wherein said step of analyzing the enhanced image includes the steps of reading out a selected non-contiguous group of the pixels of the imager and analyzing the image as represented by only the selected non-contiguous group of pixels.

8. A method for helping to control a vehicle occupant protection device, said method comprising the steps of:

taking an image of the vehicle interior with a digital imager having an array of pixels;

reading out a selected non-contiguous group of the pixels of the imager that are representative of the entire image, to estimate the illumination levels across the entire array of pixels;

analyzing the image to detect at least one of features and characteristics of the image; and

controlling operation of the vehicle occupant protection device on the basis of the image analysis.

7. A method as set forth in claim 9 wherein the selected group of pixels comprises predetermined pixels selected from predetermined rows of the pixel array of the imager.

9. A method as set forth in claim 8 further including the steps of preliminarily analyzing the entire image as represented by the selected group of pixels after performing said reading step and before performing said analyzing step, and enhancing one or more portions of the image to make an enhanced image on the basis of the preliminary analysis, and wherein said step of analyzing the image to detect at least one of features and characteristics of the image includes analyzing the enhanced image.

10. A method as set forth in claim 8 including the steps of:

taking a second image of the vehicle interior with the a digital imager;

reading out a selected non-contiguous group of the pixels of the imager that are representative of the entire second image, to estimate the illumination levels across the entire array of pixels; and

comparing the selected group of pixels from the first mage to the selected group of pixels of the second image, to detect motion in the vehicle interior.

11. A method as set forth in claim 8 further comprising the steps of changing the shutter speed of the imager on the basis of the estimated illumination levels, and taking a second image of the vehicle interior with the changed shutter speed.

12. A method as set forth in claim 8 further comprising the steps of passing the image through an amplifier, and varying the gain of the amplifier on the basis of the estimated illumination levels.

13. A method for helping to control a vehicle occupant protection device, said method comprising the steps of:

taking a first image of the vehicle interior with a digital imager having an array of pixels and set at a first shutter speed;

reading out at least a portion of the pixels of the imager to determine illumination levels of the image;

changing the shutter speed of the imager from the first shutter speed to a second shutter speed;

taking a second image of the vehicle interior with the digital imager set at a second shutter speed;

analyzing the second image to detect at least one of features and characteristics of the image; and

controlling operation of the vehicle occupant protection device on the basis of the image analysis.

14. A method as set forth in claim 13 wherein said step of reading out at least a portion of the pixels of the imager to determine illumination levels of the image, includes reading out a selected non-contiguous group of the pixels of the imager that are representative of the entire image, to estimate illumination levels across the entire array of pixels.

15. A method as set forth in claim 14 wherein said step of reading out at least a portion of the pixels of the imager to determine illumination levels of the image, includes selecting a contiguous portion of the image that is less than the entire image,

applying one or more image enhancement techniques to the selected portion of the image to enhance the selected image portion;

combining the enhanced selected image portion with the other portions of the image to make an enhanced image; and

analyzing the enhanced image to detect features and/or characteristics of the enhanced image.