Occupant sensor
View Patent ↗An occupant sensor incorporates a 3-D imaging system that acquires a 3-D image of an object. The image is segmented to remove unwanted portions and to identify a region-of-interest, and the content thereof is classified responsive to a plurality of 3-D features. In one embodiment, the 3-D image is transformed to a second 3-D image from a second viewing perspective. A two-dimensional projection of the second 3-D image is classified, and a presence, size and position of occupant can be identified from features thereof. A safety restraint system is controlled responsive to the detected scenario, including the presence, position and size of an occupant.
1. A method of sensing an occupant in a vehicle, comprising:
a. providing for acquiring a first three-dimensional image of a scene from a first viewing perspective;
b. providing for segmenting said first three-dimensional image so as to identify a region-of-interest in said first three-dimensional image;
c. providing for forming a second three-dimensional image by removing a portion of said first three-dimensional image that is outside of said region-of-interest; and
d. providing for classifying a scenario responsive to an image content of said second three-dimensional image, wherein said image content is represented by a plurality of three-dimensional features selected from a volumetric central moment, a centroid, a volume, a volumetric roundness, a ratio of radii, a volume of a bounding cube, a ratio of volumes and a percentage of volume occupied.
2. A method of sensing an occupant in a vehicle as recited in claim 1 , wherein said portion of said first three-dimensional image that is outside of said region-of-interest comprises a portion of an image of an object selected from a dashboard of the vehicle, an interior of a side door of a vehicle, a scene outside a window of the vehicle, a floor of the vehicle, and a structural pillar in the vehicle.
3. A method of sensing an occupant in a vehicle as recited in claim 1 , wherein said operation of classifying comprises detecting the presence of an occupant from a plurality of said features of said second three-dimensional image.
4. A method of sensing an occupant in a vehicle as recited in claim 3 , further comprising providing for tracking said occupant from one image frame to another.
5. A method of sensing an occupant in a vehicle as recited in claim 3 , further comprising providing for detecting whether said occupant is located in an at-risk zone proximate to a safety restraint system.
6. A method of sensing an occupant in a vehicle as recited in claim 3 , further comprising providing for determining a size of said occupant from at least one feature of said second three-dimensional image.
7. A method of sensing an occupant in a vehicle as recited in claim 1 , further comprising providing for controlling a safety restraint system responsive to said operation of classifying a scenario.
8. A method of sensing an occupant in a vehicle, comprising:
a. providing for acquiring a first three-dimensional image of a scene from a first viewing perspective;
b. providing for transforming said first three-dimensional image to a second three-dimensional image from a second viewing perspective;
c. providing for segmenting either said first three-dimensional image prior to said transforming operation, or said second three-dimensional image, so as to identify a region-of-interest in said first or said second three-dimensional image;
d. providing for forming a third three-dimensional image by removing a portion of said first or said second three-dimensional image that is outside of said region-of-interest; and
e. providing for classifying a scenario responsive to an image content of said third three-dimensional image, wherein said image content comprises a two-dimensional representation of said third three-dimensional image.
9. A method of sensing an occupant in a vehicle as recited in claim 8 , wherein said portion of said first or said second three-dimensional image that is outside of said region-of-interest comprises a portion of an image of an object selected from a dashboard of the vehicle, an interior of a side door of a vehicle, a scene outside a window of the vehicle, a floor of the vehicle, and a structural pillar in the vehicle.
10. A method of sensing an occupant in a vehicle as recited in claim 8 , wherein said image content is represented by at least one two-dimensional feature selected from a central moment, a normalized central moment, an invariant moment, a perimeter, and area, a roundness, a bending energy, an orientation, an area of a bounding rectangle, a best fit ellipses, and eccentricity of a region of interest, a ratio of areas, and a central axis line.
11. A method of sensing an occupant in a vehicle as recited in claim 10 , wherein said operation of classifying comprises detecting the presence of an occupant from a plurality of said features of said third three-dimensional image.
12. A method of sensing an occupant in a vehicle as recited in claim 11 , further comprising providing for tracking said occupant from one image frame to another.
13. A method of sensing an occupant in a vehicle as recited in claim 11 , further comprising providing for detecting whether said occupant is located in an at-risk zone proximate to a safety restraint system.
14. A method of sensing an occupant in a vehicle as recited in claim 11 , further comprising providing for determining a size of said occupant from at least one feature of said third three-dimensional image.
15. A method of sensing an occupant in a vehicle as recited in claim 8 , further comprising providing for controlling a safety restraint system responsive to said operation of classifying a scenario.