초록 ▼

An eye-safe light curtain is generated by a plurality of LED's illuminating a cylindrical lens having a corrugated cylindrical surface. A camera generates a first image of an avoidance zone boundary of an air bag inflator with the light curtain off, and a second image of with the light curtain on al

An eye-safe light curtain is generated by a plurality of LED's illuminating a cylindrical lens having a corrugated cylindrical surface. A camera generates a first image of an avoidance zone boundary of an air bag inflator with the light curtain off, and a second image of with the light curtain on along the avoidance zone boundary. The first image is subtracted from the second image, and the resulting difference image is binned to enhance signal strength. A penetration of the avoidance zone is classified from features of the leading edge of the binned image, and the air bag inflator is disabled if the avoidance zone is penetrated by an occupant at risk of injury from the deployment thereof. An image of the light curtain may be recovered for high ambient lighting conditions by adapting the exposure time of the camera responsive to the percentage of pixels in a mask region of the first image having values exceeding a threshold.

대표청구항 ▼

1. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator, comprising:a. generating an image signal representative of a first image of said region of space from a first location, wherein said region of spac

1. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator, comprising:a. generating an image signal representative of a first image of said region of space from a first location, wherein said region of space includes the bounding surface of the avoidance zone, and said image signal is generated responsive to an exposure time;b. projecting from a second location a light curtain substantially parallel to and along a first surface, wherein said light curtain has a thickness within a cross-section normal to said first surface, said thickness is adapted so that an intensity of said light curtain within said cross-section is less than a first threshold, said first threshold corresponds to an intensity level that is safe for direct viewing by a human eye, and said first surface is proximate to the bounding surface of said avoidance zone;c. generating an image signal representative of a second image of said region of space from said first location, wherein said region of space is intersected by said light curtain when said light curtain is activated;d. subtracting said first image from said second image so as to form a difference image;e. forming a binned image value of a binned image by accumulating a plurality of pixel values within a region of said difference image;f. repeating the operation of forming said binned image value for a plurality of adjacent regions of said difference image;g. detecting from said binned image a leading edge associated with an image of said light curtain; andh. determining whether or not an object is located in said avoidance zone responsive to a comparison of said leading edge with a reference image signal representing a boundary of said avoidance zone.2. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, wherein said first location is proximate to a headliner of the vehicle.3. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 2, wherein said first location is proximate to the centerline of the vehicle.4. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, further comprising:a. identifying a mask region within said first image, wherein said mask region at least partially surrounds a region illuminated by said light curtain;b. determining the number of pixels within said mask region having pixel values greater than a first threshold; andc. comparing said number of pixels with a second threshold, and if said number of pixels exceeds said second threshold, then reducing said exposure time and recapturing said first image.5. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, wherein said first surface comprises a plane.6. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, wherein said first surface is substantially vertical.7. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, wherein said first location is displaced rearwards from said second location.8. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, further comprising:a. determining the maximum value of a pixel of said second image; andb. comparing said maximum value with a third threshold, and if said maximum value is less than said third threshold, then increasing said exposure time for a subsequent operation of generating an image signal.9. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, wherein said light curtain comprises near-infrared light, and the operations of capturing said first and second images comprise capturing light that is within a frequency range that includes at least one frequency of said near-infrared light.10. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, wherein at least one of said operations of generating an image signal, subtracting said first image from said second image, forming a binned image value, and detecting a leading edge are substantially limited to a region of said first and second images that is on one side of a lower boundary of said avoidance zone.11. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, further comprising:a. detecting the portion of said leading edge that corresponds to a region within said avoidance zone;b. determining at least one feature of said portion of said leading edge that corresponds to a region within said avoidance zone; andc. classifying the penetration of said avoidance zone, responsive to at least one comparison of said at least one feature with a corresponding at least one set of reference values of said at least one feature.12. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 1, wherein said at least one feature comprises a plurality of features, and said operation of classifying the penetration of said avoidance zone comprises determining a plurality of most likely classifications, each of said plurality of most likely classifications is based upon a comparison of one of said plurality of features with associated reference values for said one of said plurality of features for each possible result of said classification, and determining a resultant most likely classification by tallying said plurality of most likely classifications.13. A method of detecting a penetration of a bounding surface of an avoidance zone in a region of space of in a vehicle proximate to an air bag inflator as recited in claim 11, further comprising controlling the actuation of the air bag inflator responsive the classification of said penetration of said avoidance zone.14. A method of processing an image, comprising:a. capturing a first image with an image sensor, wherein said first image comprises a first plurality of pixels, each pixel of said first plurality of pixels has a first pixel value, and said first plurality of pixels of said first image has an associated first plurality of first pixel values;b. storing said plurality of first pixel values in a first memory;c. capturing a second image with said image sensor, wherein said second image comprises said first plurality of pixels, each pixel of said first plurality of pixels has a second pixel value, said first plurality of pixels of said second image has an associated first plurality of second pixel values, and for both of said first image and said second image, said first plurality of pixels correspond to an array of a second plurality of rows and a third plurality of columns;d. for a fourth plurality of said first plurality of pixels along one of said rows, or for a fifth plurality of said first plurality of pixels along one of said columns, performing a set of steps comprising:i. computing a difference value as a difference between said first pixel value and said second pixel value for a corresponding pixels in said first image and said second image;ii. replacing said first pixel value with said second pixel value in said first memory; andiii. adding said difference value to a first accumulated value in a second memory that is initialized to zero;e. adding said first accumulated value to a second accumulated value in a third memory that is initialized to zero; andf. if step d is performed along one of said rows, then repeating steps d and e for different adjacent columns until a fifth plurality of said first accumulated values have been added to said second accumulated value, otherwise, if step d is performed along one of said columns, then repeating steps d and e for different adjacent rows until a fourth plurality of said first accumulated values have been added to said second accumulated value.15. A method of processing an image as recited in claim 14, wherein steps d and e are performed for either an entire said row or an entire said column before proceeding with step f.