Method of estimating and correcting camera rotation with vanishing point location

• US 6,968,094 B1
• Filed: 09/15/2000
• Issued: 11/22/2005
• Est. Priority Date: 03/27/2000
• Status: Expired due to Fees

• Current Assignee: Eastman Kodak Company
• Original Assignee: Eastman Kodak Company
• Inventors: Gallagher, Andrew C.
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): Rosario, Dennis
• Application Number:
  US09/663,056
• Time in Patent Office: 1,894 Days
• Field of Search: 382/296, 382/151, 382/290, 382/289, 382/288, 382/295
• US Class Current: 382/296
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: H04N 23/68 for stable pick-up of the scene, e.g. compensating for camera body vibrations
• CPC Class Codes: H04N 23/6811 based on the image signal
• CPC Class Codes: H04N 23/6812 based on additional sensors, e.g. acceleration sensors

Abstract

A method of generating an image transform for modifying a digital image, that includes the steps of: detecting a vanishing point related to the selected image; determining a preferable vanishing point location, and generating an image transform based on the vanishing point location and the preferable vanishing point location. In another embodiment, the present invention provides a method for detecting an amount of rotation between the vertical axes of a scene and an image of the scene, that includes the steps of: detecting a set of vanishing points related to the image; selecting a set of vanishing points corresponding to a vertical axis of the scene based on a predetermined criteria; and using the selected vanishing points to detect the rotation of the image.

Claims

1. A method of detecting an amount of rotation between the vertical axes of a scene and an image of the scene, comprising:

a) detecting a set of vanishing points related to the image;

b) selecting a set of vanishing points corresponding to a vertical axis of the scene based on a predetermined criteria, wherein the predetermined criteria is a threshold operation to select a vanishing point that is greater than a predetermined distance from the center of the image; and

c) using the selected vanishing points to detect the rotation of the image.

2. The method claimed in claim 1, wherein the image has x′

and y′

axes and the predetermined criteria is;

|x_G|>

T₁

OR

|y_G|>

T₁

where the vanishing points are represented by vanishing point vectors v_G=(x_G, y_G, z_G) with relation to a Gaussian sphere located on a z-axis with respect to the image at a distance f away from the image plane, f representing an approximation of the focal length of a camera lens employed to photograph the image; and

T₁, is a predetermined constant; and

the rotation is determined by calculating the angles between an x or y axis of the Gaussian sphere and the selected vanishing point vectors and choosing the smallest angle as the rotation.

3. The method claimed in claim 2, wherein 0.3<

T₁<

1, and the angles between they axis and the vanishing point vector are

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(v_Gxy·

[0,1,0])

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(v_Gxy·

[0,−

1,0])

and the angle between the x axis and the vanishing point vector is

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(v_Gxy·

[1,0,0])

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(^v_Gxy·

[−

1,0,0])

where $v_{\mathrm{Gxy}}=\frac{\left[x_G,y_G,0\right]}{\sqrt{x_G^2+y_G^2}}$

and sign(x_Gy_G) is 1 if the signs of x_G and y_G are similar and sign(x_Gy_G) is −

1 if the signs of x_G and y_G are dissimilar.

4. A computer readable medium having computer executable instructions for performing the method of claim 2.

5. A computer readable medium having computer executable instructions for performing the method of claim 3.

6. The method claimed in claim 1, wherein the image has x′

and y′

axes and the predetermined criteria is;

|x_G|>

T₁

OR

|y_G|>

T₁

where the vanishing points are represented by vanishing point vectors v_G=(x_G, y_G, z_G) with relation to a Gaussian sphere located on a z-axis with respect to the image at a distance f away from the image plane, f representing an approximation of the focal length of a camera lens employed to photograph the image; and

T₁, is a predetermined constant; and

the rotation is determined by calculating the angles between an axis of the Gaussian sphere parallel to the vertical axis of the image and the selected vanishing point vectors and choosing the smallest angle as the rotation.

7. The method claimed in claim 6, wherein T₁=0.5.

8. A computer readable medium having computer executable instructions for performing the method of claim 6.

9. A computer readable medium having computer executable instructions for performing the method of claim 7.

10. A computer readable medium having computer executable instructions for performing the method of claim 1.

11. An apparatus for detecting an amount of rotation between the vertical axes of a scene and an image of the scene, comprising:

a) means for detecting a set of vanishing points related to the image;

b) means for selecting a set of vanishing points corresponding to a vertical axis of the scene based on a predetermined criteria, wherein the predetermined criteria is a threshold operation to select a vanishing point that is greater than a predetermined distance from the center of the image; and

c) means for using the selected vanishing points to detect the rotation of the image.

12. The apparatus claimed in claim 11, wherein the image has x′

and y′

axes and the predetermined criteria is;

|x_G|>

T₁

OR

|y_G|>

T₁

where the vanishing points are represented by vanishing point vectors v_G=(x_G, y_G, z_G) with relation to a Gaussian sphere located on a z-axis with respect to the image at a distance f away from the image plane, f representing an approximation of the focal length of a camera lens employed to photograph the image; and

T₁, is a predetermined constant; and

the rotation is determined by calculating the angles between an x or y axis of the Gaussian sphere and the selected vanishing point vectors and choosing the smallest angle as the rotation.

13. The apparatus claimed in claim 12, wherein 0.3<

T₁<

1, and the angles between they axis and the vanishing point vector are

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(v_Gxy·

[0,1,0])

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(v_Gxy·

[0,−

1,0])

and the angle between the x axis and the vanishing point vector is

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(v_Gxy·

[1,0,0])

γ

=sign(x_Gy_G)cos<sup>−

1</sup>(v_Gxy·

[−

1,0,0])

where $v_{\mathrm{Gxy}}=\frac{\left[x_G,y_G,0\right]}{\sqrt{x_G^2+y_G^2}}$

and sign(x_Gy_G) is 1 if the signs of x_G and y_G are similar and sign(x_Gy_G) is −

1 if the signs of x_G and y_G are dissimilar.

14. The apparatus claimed in claim 13, wherein T₁=0.5.

15. The apparatus claimed in claim 11, wherein the image has x′

and y′

axes and the predetermined criteria is;

|x_G|>

T₁

OR

|y_G|>

T₁

where the vanishing points are represented by vanishing point vectors v_G=(x_G, y_G, z_G) with relation to a Gaussian sphere located on a z-axis with respect to the image at a distance f away from the image plane, f representing an approximation of the focal length of a camera lens employed to photograph the image; and

T₁, is a predetermined constant; and

the rotation is determined by calculating the angles between an axis of the Gaussian sphere parallel to the vertical axis of the image and the selected vanishing point vectors and choosing the smallest angle as the rotation.