Determining distance between an object and a capture device based on captured image data
View Patent ↗In various embodiments, methods, systems, and computer program products for determining distance between an object and a capture device are disclosed. The distance determination techniques are based on image data captured by the capture device, where the image data represent the object. These techniques improve the function of capture devices such as mobile phones by enabling determination of distance using a single lens capture device, and based on intrinsic parameters of the capture device, such as focal length and scaling factor(s), in preferred approaches. In some approaches, the distance estimation may be based in part on a priori knowledge regarding size of the object represented in the image data. Distance determination may be based on a homography transform and/or reference image data representing the object, a same type or similar type of object, in more approaches.
1. A method, comprising:
determining a distance between an object and a capture device based on:
image data captured by the capture device, the image data representing the object; and
a capture device intrinsic parameter matrix A;
wherein:
A
=
(
f
/
dx
c
d
f
/
dy
e
1
)
;
wherein f is a capture device focal length;
wherein dx and dy are scaling factors of the capture device;
wherein c is a skew parameter; and
wherein d and e are coordinates of a corresponding principal point in the image data.
2. The method as recited in claim 1 , wherein determining the distance further comprises estimating a normalized homography matrix {tilde over (H)}.
3. The method as recited in claim 1 , comprising determining the capture device focal length using an API call to the capture device.
4. The method of claim 1 , wherein determining the distance between the object and the capture device is further based on: reference image data generated by scanning a reference object using a scanner or multifunction printer, the reference object corresponding to the object but different than the object, and the reference image data being characterized by a capture angle normal to the reference object.
5. The method as recited in claim 1 , wherein the image data captured by the capture device are characterized by a capture angle deviating from an angle normal to the object.
6. The method as recited in claim 1 , wherein the determining is further based on a translation vector of the object relative to the capture device.
7. The method as recited in claim 4 , wherein the reference image data are characterized by the reference object having a known aspect ratio.
8. The method as recited in claim 1 , comprising determining one or more intrinsic capture device parameters based at least in part on:
the capture device focal length; and
a size of the object;
wherein the intrinsic capture device parameters comprise the scaling factors: dx and dy;
wherein the capture device focal length is determined using an API call to the capture device; and
wherein the size of the object is known a priori.
9. The method as recited in claim 1 , comprising determining one or more intrinsic capture device parameters based at least in part on:
the capture device focal length; and
a size of the object;
wherein the intrinsic capture device parameters comprise a scaling factor a in a homography transform H;
wherein the capture device focal length is determined using an API call to the capture device; and
wherein the size of the object is known a priori.
10. The method as recited in claim 1 ,
further comprising normalizing one or more of the scaling factors;
wherein the normalizing is based on a homography transform H;
wherein H=σA(r 1 ,r 2 ,t); and
wherein σ is a scaling factor constant.
11. The method as recited in claim 1 , wherein determining the distance comprises estimating a homography transform H;
wherein H satisfies an expression λp i =HP′ 1 ; and
wherein:
λ=a focal distance between a three-dimensional reference coordinate position (X, Y, Z) and a corresponding reference coordinate position of a capture device;
p i =(x i ,y i ,1) T ;
P′ 1 =(X i ,Y i ,1) T ; and
i is a respective index feature of a point p or P′ in a corresponding image.
12. A system, comprising:
a processor configured to execute logic; and
logic configured to determine a distance between an object and a capture device based on image data captured by the capture device, the image data representing the object;
wherein the determining is based on a capture device intrinsic parameter matrix A;
wherein:
A
=
(
f
/
dx
c
d
f
/
dy
e
1
)
;
and
wherein f is a capture device focal length;
wherein dx and dy are scaling factors of the capture device;
wherein c is a skew parameter; and
wherein d and e are coordinates of a corresponding principal point in the image data.
13. A computer program product comprising a non-transitory computer readable storage medium having computer readable program code stored thereon, the computer readable program code configured to cause a processor, upon execution thereof, to:
determine a distance between an object and a capture device based on:
image data captured by the capture device, the image data representing the object; and
a capture device intrinsic parameter matrix A;
wherein:
A
=
(
f
/
dx
c
d
f
/
dy
e
1
)
;
wherein f is a capture device focal length;
wherein dx and dy are scaling factors of the capture device;
wherein c is a skew parameter; and
wherein d and e are coordinates of a corresponding principal point in the image data.
14. The method as recited in claim 1 , wherein the capture device is a mobile phone.
15. The method as recited in claim 1 , wherein the image data represent the object according to a single camera plane.
16. The computer program product of claim 13 , wherein the determining is further based on reference image data generated by scanning a reference object using a scanner or multifunction printer, the reference object corresponding to the object but different than the object, and the reference image data being characterized by a capture angle normal to the reference object.
17. The computer program product of claim 13 , wherein the image data captured by the capture device are characterized by a capture angle deviating from an angle normal to the object.
18. The computer program product of claim 17 , wherein the capture angle deviates from normal by an amount in a range from at least about 10 degrees to about 30 degrees.