US 7,406,181 B2Granted

Occupant detection system

AssigneeAutomotive Systems Laboratory, Inc.

InventorsMichael E. O'Boyle, Owen A. Davies, Gregory G. Schamp, James C. Demro

Life of this patent

Estimating the term…

Loading patent…

Abstract

A camera (32) captures successive images of light stripes (22) projected onto an object by a light curtain (18) positioned by a light source positioner (28). A background image is subtracted (616) therefrom, and the resulting image is boosted by binning (618), binarized with a thresholding algorithm (620), skeletonized (622), interpolated (624) and stored (626). Interpolated images are acquired for a plurality of light stripes (22). A processor (30) generates (1604) a 3-D surface model from Cartesian coordinates computed for non-zero camera pixels. A volumetric representation is determined (1610) from the offset of the object surface model relative to a model of a proximate surface, e.g. a seating surface (24). The object is classified (1614), e.g. by a trainable pattern recognitions system, responsive to 3-D shape descriptors (1606) of the 3-D surface model and to the volumetric representation (1610) or portions (1612) thereof. The detection of an occupant (14) in a vehicle (12) may be used to control a safety restraint system (36).

Claims55

Dependent claims

A method of detecting an object, comprising:

a. setting an exposure time for a process of generating an image signal;
b. generating an image signal representative of a first image of the object, wherein said image signal is generated by a camera at a first location, and said image signal is generated responsive to said exposure time;
c. projecting from a second location at least one beam of light across at least a portion of the object so as to provide for generating at least one image of at least one light stripe of a plurality of light stripes across said object, wherein said second location is displaced from said first location, an intensity of each light stripe of said plurality of light stripes is less than a first threshold, and said first threshold corresponds to an intensity level that is safe for direct viewing by a human eye;
d. generating at least one image signal representative of at least one second image from said camera, wherein said at least one second image is responsive to said at least one beam of light projected on said object;
e. subtracting said first image from said at least one second image so as to form at least one difference image signal of at least one difference image;
f. processing said at least one difference image so as generate a corresponding at least one fourth image, wherein a signal level of at least a portion of said at least one fourth image associated with said at least one light stripe in said at least one fourth image is boosted relative to a corresponding signal level in said at least one second image, wherein the operation of processing said at least one difference image so as to generate said corresponding at least one fourth image comprises:
i. forming a binned image value of a binned image by accumulating a plurality of pixel values within a region of said at least one difference image;
and
ii. repeating the operation of forming said binned image value for a plurality of adjacent regions of said at least one diffference image;
and
g. determining at least one profile of said object responsive to said at least one fourth image.

8 more elements

A method of detecting an object, comprising:

a. setting an exposure time for a process of generating an image signal;
b. generating an image signal representative of a first image of the object, wherein said image signal is generated by a camera at a first location, and said image signal is generated responsive to said exposure time;
c. projecting from a second location at least one beam of light across at least a portion of the object so as to provide for generating at least one image of at least one light strite of a plurality of light stripes across said object, wherein said second location is displaced from said first location, an intensity of each light stripe of said plurality of light stripes is less than a first threshold, said first threshold corresponds to an intensity level that is safe for direct viewing by a human eye;
d. generating at least one image signal representative of at least one second image from said camera, wherein said at least one second image is responsive to said at least one beam of light projected on said object;
e. subtracting said first image from said at least one second image so as to form at least one difference image signal of at least one difference image;
f. processing said at least one difference image so as generate a corresponding at least one fourth image, wherein a signal level of at least a portion of said at least one fourth image associated with said at least one light stripe in said at least one fourth image is boosted relative to a corresponding signal level in said at least one second image;
and
g. determining at least one profile of said object responsive to said at least one fourth image;
and
h. generating a characterization of at least one proximate surface proximate to which the object is located.

7 more elements

A method of detecting an object, comprising:

a. setting an exposure time for a process of generating an image signal;
b. generating an image signal representative of a first image of the object, wherein said image signal is generate by a camera at a first location, and said image signal is generated responsive to said exposure time;
c. projeting from a second location at least one beam of light across at least a portion of the object so as to provide for generating at least one image of at least one light stripe of a plurality of light stripes across said object, wherein said second location is displace from said first location, an intensity of each light stripe of said plurality of light strives is less than a first threshold, and said first threshold corresponds to an intensty level that is safe for direct viewing by a human eye;
d. generating at least one image signal representative of at least one second image from said camera, wherein said at least one second image is responsive to said at least one beam of light projected on said object;
e. subtracting said first image from said at least one second image so as to form at least one difference image signal of at least one difference image;
f. processing said at least one difference image so as generate a corresponding at least one fourth image, wherein a signal level of at least a portion of said at least one fourth image associated with said at least one light stripe in said at least one fourth image is boosted relative to a corresponding signal level in said at least one second image;
g. determining at least one profile of said object responsive to said at least one fourth image;
h. determining at least one feature of said object responsive to said at least one profile, and
i. classifying said object responsive to said at least one feature.

6 more elements

A method of providing for detecting an object, comprising:

a. providing for setting an exposure time for a process of generating an image signal;
b. providing for generating an image signal representative of a first image of the object, wherein said image signal is generated by a camera at a first location, and said image signal is generated responsive to said exposure time;
c. providing for projecting from a second location at least one beam of light across at least a portion of the object so as to provide for generating at least one image of at least one light stripe of a plurality of light stripes across said object, wherein said second location is displaced from said first location, an intensity of each light stripe of said plurality of light stripes is less than a first threshold, and said first threshold corresponds to an intensity level that is safe for direct viewing by a human eye;
d. providing for generating at least one image signal representative of at least one second image from said camera, wherein said at least one second image is responsive to said at least one beam of light projected on said object;
e. providing for subtracting said first image from said at least one second image so as to form at least one difference image signal of at least one difference image;
f. providing for processing said at least one difference image so as generate a corresponding at least one fourth image, wherein a signal level of at least a portion of said at least one fourth image associated with said at least one light stripe in said at least one fourth image is boosted relative to a corresponding signal level in said at least one second image, wherein the operation of processing said at least one difference image so as to generate said corresponding at least one fourth image comprises:
i. forming a binned image value of binned image by accumulating a plurality of pixel values within a region of said at least one difference image;
and
ii. repeating the operation of forming said binned image value for a plurality of adjacent regions of said at least one difference image;
and
g. providing for determining at least one profile of said object responsive to said at least one fourth image.

8 more elements

A method of providing for detecting an, comprising:

a. providing for setting an exposure time for a process of generating an image signal;
b. providing for generating an image signal representative of a first image of the object, wherein said image signal is generated by a camera at a first location, and said image signal is generated responsive to said exposure time;
c. providing for adjusting said exposure time responsive to at least a portion of said first image so as to either reduce saturation or increase dynamic range of at least a portion of said first image;
d. providing for projecting from a second location at least one beam of light across at least a potion of the object so as to provide for generating at least one image of at least one light stripe of a plurality of light stripes across said object, wherein said second location is displaced from said first location, an intensity of each light stripe of said plurality of ligth stripes is less than a first threshold, and said first threshold corresponds to an intensity level that is safe for direct viewing by a human eye;
e. providing for generating at least one image signal representative of at least one second image from said camera, wherein said at least one second image is responsive to said at least one beam of light projected on said object;
f. providing for subtracting said first image from said at least one second image so as to form at least one difference image signal of at least one difference image;
g. providing for processing said at least one difference image so as generate a corresponding at least one fourth image, wherein a signal level of at least a portion of said at least one fourth image associated with said at least one light stripe in said at least one fourth image is boosted relative to a corresponding signal level in said at least one second image;
and
h. providing for determining at least one profile of said object responsive to said at least one fourth image.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 10/957,968Filed 4 Oct 2004 · us provisional application
Priority: 3 Oct 2003
Published: US 2005/0111700 A126 May 2005
Granted: 29 Jul 2008
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

B60R 21/01538
Using field detection presence sensors: for image processing, e.g. cameras or sensor arrays
B60R 21/01556
Including means for detecting the presence or position of passengers, passenger seats or child seats , and the related safety parameters…
G06V 10/145
Optical characteristics of the device performing the acquisition or on the illumination arrangements: illumination specially adapted for pattern…
G06V 20/59
Context or environment of the image: inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions