Determining a number of objects in an IR image
First Claim
Patent Images
1. A method for determining the number of objects in an IR image obtained by an IR imaging system, the method comprising:
- collecting a total of N intensity values for each pixel in an IR image said intensity values having been collected using an IR imaging system comprising a single IR detection device and a sequentially illuminating N band IR Illuminator, where (N≧
3), with one fixed filter, said intensity values comprising;
Ic(i)=α
∫
λ
1λ
2Isi(λ
)[TG2(λ
)Ro(λ
)+η
RG(λ
)]TL(λ
)D(λ
)dλ
+Ib where i=1 . . . N, such that i is the ith IR band from said illuminator that is sequentially illuminating, α
is a constant that depends on an angle and distance from said illumination source, an attenuation of an IR wave in the air, and an integration time of said detecting device, Ib is a background intensity, Ro(λ
) is a reflectance of an object detected by said detection device, RG(λ
) and TG(λ
) are a reflectance and a transmittance of glass, otherwise RG(λ
)=0 and TG(λ
)=1, constant η
is a percentage of light reflected from glass and received by said detector, otherwise η
=0, TL(λ
) is a transmittance of said fixed filter, and D(λ
) is a responsivity of said detection device;
determining a classification for each pixel in said IR image using one of;
a best fitting method of a reflectance, and a correlation method; and
determining a total number of objects in said IR image based upon said pixel classification.
4 Assignments
0 Petitions
Accused Products
Abstract
What is disclosed is a novel system and method for determining the number of objects in an IR image obtained using an IR imaging system. In one embodiment, a total of N intensity values are collected for each pixel in an IR image using a IR imaging system comprising an IR detection device and an IR Illuminator. Intensity values are retrieved from a database which have been estimated for a plurality of known materials, such as skin and hair. A classification is determined for each pixel in the IR image using either a best fitting method of a reflectance, or a correlation method. Upon classification, a total number of objects in the IR image can be determined. The present system and method finds its intended uses in of real world applications such as, determining the number of occupants in a vehicle traveling in a HOV/HOT lane.
18 Citations
24 Claims
-
1. A method for determining the number of objects in an IR image obtained by an IR imaging system, the method comprising:
-
collecting a total of N intensity values for each pixel in an IR image said intensity values having been collected using an IR imaging system comprising a single IR detection device and a sequentially illuminating N band IR Illuminator, where (N≧
3), with one fixed filter, said intensity values comprising;
Ic(i)=α
∫
λ
1λ
2Isi(λ
)[TG2(λ
)Ro(λ
)+η
RG(λ
)]TL(λ
)D(λ
)dλ
+Ibwhere i=1 . . . N, such that i is the ith IR band from said illuminator that is sequentially illuminating, α
is a constant that depends on an angle and distance from said illumination source, an attenuation of an IR wave in the air, and an integration time of said detecting device, Ib is a background intensity, Ro(λ
) is a reflectance of an object detected by said detection device, RG(λ
) and TG(λ
) are a reflectance and a transmittance of glass, otherwise RG(λ
)=0 and TG(λ
)=1, constant η
is a percentage of light reflected from glass and received by said detector, otherwise η
=0, TL(λ
) is a transmittance of said fixed filter, and D(λ
) is a responsivity of said detection device;determining a classification for each pixel in said IR image using one of;
a best fitting method of a reflectance, and a correlation method; anddetermining a total number of objects in said IR image based upon said pixel classification. - View Dependent Claims (2, 4, 5, 6, 14)
-
-
4. The method of claim 1, wherein said best fitting reflectance method comprises:
-
cross-referencing an intensity value associated with said pixels with at least one calculated intensity value using a known reflectance retrieved from a database; and classifying said pixel based upon a best fitting reflectance.
-
-
5. The method of claim 1, wherein said database further contains any of:
- a power spectra of said illuminator, a transmittance of a filter, a responsivity curve, and a quantum efficiency curve of a detector on said IR detection device.
-
6. The method of claim 1, further comprising combining any of said pixel intensity values to generate at least one new intensity value for said pixel.
-
14. The method of claim 1, wherein said objects are human occupants in a motor vehicle.
-
3. A method for determining the number of objects in an IR image obtained by an IR imaging system, the method comprising:
-
collecting a total of N intensity values for each pixel in an IR image using an IR imaging system comprising N IR detection devices with N band pass filters where (N≧
3), and a single IR Illuminator covering a wavelength range of said filters, said intensity values comprising;
Ic(i)=α
∫
λ
1λ
2Is(λ
)[TG2(λ
)Ro(λ
)+η
RG(λ
)]TLi(λ
)D(λ
)dλ
+Ibwhere i=1 . . . N, such that i is the ith IR band pass filter, α
is a constant that depends on an angle and distance from said illumination source, an attenuation of an IR wave in the air, and an integration time of said detecting device, Ib is a background intensity, Ro(λ
) is a reflectance of an object detected by said detection device, RG(λ
) and TG(λ
) are a reflectance and a transmittance of glass, otherwise RG(λ
)=0 and TG(λ
)=1, constant η
is a percentage of light reflected from glass and received by said detector, otherwise η
=0, TLi(λ
) is a transmittance of the ith filter, and D(λ
) is a responsivity of said detection device;determining a classification for each pixel in said IR image using one of;
a best fitting method of a reflectance, and a correlation method; anddetermining a total number of objects in said IR image based upon said pixel classification. - View Dependent Claims (13, 15, 16, 17, 18)
-
-
15. The method of claim 13, wherein said best fitting reflectance method comprises:
-
cross-referencing an intensity value associated with said pixels with at least one calculated intensity value using a known reflectance retrieved from a database; and classifying said pixel based upon a best fitting reflectance.
-
-
16. The method of claim 13, wherein said database further contains any of:
- a power spectra of said illuminator, a transmittance of a filter, a responsivity curve, and a quantum efficiency curve of a detector on said IR detection device.
-
17. The method of claim 13, further comprising combining any of said pixel intensity values to generate at least one new intensity value for said pixel.
-
18. The method of claim 3, wherein said objects are human occupants in a motor vehicle.
-
7. A system for determining the number of objects in an IR image, the system comprising:
-
a memory and a storage medium; and a processor in communication with and said storage medium and said memory, said processor executing machine readable instructions for performing the method of; collecting a total of N intensity values for each pixel in an IR image using an IR imaging system comprising a single IR detection device and a sequentially illuminating N band IR Illuminator, where (N≧
3), with one fixed filter, said intensity values comprising;
Ic(i)=α
∫
λ
1λ
2Isi(λ
)[TG2(λ
)Ro(λ
)+η
RG(λ
)]TL(λ
)D(λ
)dλ
+Ibwhere i=1 . . . N, such that i is the ith IR band from said illuminator that is sequentially illuminating, α
is a constant that depends on an angle and distance from said illumination source, an attenuation of an IR wave in the air, and an integration time of said detecting device, Ib is a background intensity, Ro(λ
) is a reflectance of an object detected by said detection device, RG(λ
) and TG(λ
) are a reflectance and a transmittance of glass, otherwise RG(λ
)=0 and TG(λ
)=1, constant η
is a percentage of light reflected from glass and received by said detector, otherwise η
=0, TL(λ
) is a transmittance of said fixed filter, and D(λ
) is a responsivity of said detection device;determining a classification for each pixel in said IR image using one of;
a best fitting method of a reflectance, and a correlation method; anddetermining a total number of objects in said IR image based upon said pixel classification. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
9. The system of claim 7, wherein said best fitting reflectance method comprises:
-
cross-referencing an intensity value associated with said pixels with at least one calculated intensity value using a known reflectance retrieved from a database; and classifying said pixel based upon a best fitting reflectance.
-
-
10. The system of claim 7, wherein said database further contains any of:
- a power spectra of said illuminator, a transmittance of a filter, a responsivity curve, and a quantum efficiency curve of a detector on said IR detection device.
-
11. The system of claim 7, further comprising combining any of said pixel intensity values to generate at least one new intensity value for said pixel.
-
12. The system of claim 7, wherein said objects are human occupants in a motor vehicle.
-
19. A system for determining the number of objects in an IR image, the system comprising:
-
a memory and a storage medium; and a processor in communication with and said storage medium and said memory, said processor executing machine readable instructions for performing the method of; collecting a total of N intensity values for each pixel in an IR image using an IR imaging system comprising N IR detection devices with N band pass filters where (N≧
3), and a single IR Illuminator covering a wavelength range of said filters, said intensity values comprising;
Ic(i)=α
∫
λ
1λ
2Is(λ
)[TG2(λ
)Ro(λ
)+η
RG(λ
)]TLi(λ
)D(λ
)dλ
+Ibwhere i=1 . . . N, such that i is the ith IR band pass filter, α
is a constant that depends on an angle and distance from said illumination source, an attenuation of an IR wave in the air, and an integration time of said detecting device, Ib is a background intensity, Ro(λ
) is a reflectance of an object detected by said detection device, RG(λ
) and TG(λ
) are a reflectance and a transmittance of glass, otherwise RG(λ
)=0 and TG(λ
)=1, constant η
is a percentage of light reflected from glass and received by said detector, otherwise η
=0, TLi(λ
) is a transmittance of the ith filter, and D(λ
) is a responsivity of said detection device;determining a classification for each pixel in said IR image using one of;
a best fitting method of a reflectance, and a correlation method; anddetermining a total number of objects in said IR image based upon said pixel classification. - View Dependent Claims (20, 21, 22, 23, 24)
-
-
21. The system of claim 19, wherein said best fitting reflectance method comprises:
-
cross-referencing an intensity value associated with said pixels with at least one calculated intensity value using a known reflectance retrieved from a database; and classifying said pixel based upon a best fitting reflectance.
-
-
22. The system of claim 19, wherein said database further contains any of:
- a power spectra of said illuminator, a transmittance of a filter, a responsivity curve, and a quantum efficiency curve of a detector on said IR detection device.
-
23. The system of claim 19, further comprising combining any of said pixel intensity values to generate at least one new intensity value for said pixel.
-
24. The system of claim 19, wherein said objects are human occupants in a motor vehicle.
Specification
-
- Resources
Litigation Campaign Assessment
Thank you for your request. You will receive a custom alert email when the Litigation Campaign Assessment is available.
×
-
Current AssigneeConduent Business Services, LLC (Conduent, Inc.)
-
Original AssigneeXerox Corporation (Xerox Holdings Corp.)
-
InventorsWang, Yao Rong, Fan, Zhigang, Mestha, Lalit Keshav
-
Primary Examiner(s)Czekaj, David
-
Assistant Examiner(s)Owens, Tsion B
-
Application NumberUS13/086,006Publication NumberTime in Patent Office951 DaysField of Search348/164, 348/148, 382/118US Class Current348/148CPC Class CodesG06T 2207/10048 Infrared imageG06T 2207/30242 Counting objects in imageG06T 7/11 Region-based segmentationG06V 10/58 relating to hyperspectral dataG06V 40/103 Static body considered as a...
