System and method for automatically measuring the dimensions of and identifying the type of exterior siding

• US 8,977,033 B1
• Filed: 09/26/2014
• Issued: 03/10/2015
• Est. Priority Date: 03/28/2014
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Maurer, Jonathan D., Christopulos, Nicholas U.
• Primary Examiner(s): Hung, Yubin
• Application Number:
  US14/498,046
• Time in Patent Office: 165 Days
• Field of Search: 381/141, 381/286, 348/137
• US Class Current: 382/141
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/20048 Transform domain processing
• CPC Class Codes: G06T 2207/20061 Hough transform
• CPC Class Codes: G06T 2207/30108 Industrial image inspection
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning

Abstract

Methods, systems, and computer readable media are disclosed for determining a pixel-to-length ratio between a number of pixels disposed over a predetermined length of a reference object within an image of a siding sample and the predetermined length of the reference object. A first and second distance between respective first and second pairs of points within the image corresponding to respective first and second length measurements of the siding sample are determined, as well as a first and second number of pixels disposed between the first and second pair of points, respectively. Furthermore, the method, system, and computer readable medium disclose determining the first length measurement based on the pixel-to-length ratio and the first number of pixels, determining the second length measurement based on the pixel-to-length ratio and the second number of pixels, and identifying a siding product associated with the first and second length measurements.

Claims

1. A computer-implemented method for identifying siding products, comprising:

adjusting, by one or more processors, an orientation of a reference object within an image of a siding sample to align edges of the reference object with edges of the siding sample;

determining, by one or more processors, a pixel-to-length ratio representative of a ratio between a first number of pixels disposed over a length of the reference object and the length of the reference object;

determining, by one or more processors, a first siding measurement based upon the pixel-to-length ratio and a second number of pixels disposed over a first portion of the image of the siding sample corresponding to the first siding measurement; and

identifying, by one or more processors, one or more siding products associated with the first siding measurement.

2. The method of claim 1, further comprising:

determining, by one of more processors, whether the orientation of the reference object needs to be adjusted such that the edges of the reference object are aligned with edges of the siding sample; and

adjusting the orientation of the reference object only when it is determined that the orientation needs to be adjusted.

3. The method of claim 1, further comprising:

rectifying, by one or more processors, the image of the siding sample so the perspective of the siding sample faces forward if the reference object includes the perspective distortion.

4. The method of claim 1, wherein the act of adjusting the orientation of the reference object comprises:

adjusting the orientation of the reference object and the siding sample in the image such that respective horizontal and vertical edges of each of the reference object and the siding sample are aligned with edges corresponding to a horizontal-vertical plane.

5. The method of claim 1, further comprising:

determining a second siding measurement based upon the pixel-to-length ratio and a third number of pixels disposed over a second portion of the image of the siding sample corresponding to the second siding measurement,

and wherein the act of identifying the one or more siding products comprises;

identifying the one or more siding products associated with the first and the second siding measurement.

6. The method of claim 5, wherein the first siding measurement corresponds to a face size of the siding sample, and wherein the second siding measurement corresponds to a profile size of the siding sample.

7. The method of claim 6, wherein the act of identifying the one or more siding products comprises:

identifying the one or more siding products from siding products stored in the siding product reference database having a face size and a profile size matching the face size and the profile size of the siding sample.

8. The method of claim 1, further comprising:

detecting, by one or more processors, the reference object using at least one of;

a Scale-Invariant Feature Transform (SIFT);

a Speeded Up Robust Features (SURF);

a Radon transform;

or

a Hough transform.

9. A non-transitory, tangible computer-readable medium storing machine readable instructions that, when executed by a processor, cause the processor to:

adjust an orientation of a reference object within an image of a siding sample to align edges of the reference object with edges of the siding sample;

determine a pixel-to-length ratio representative of a ratio between a first number of pixels disposed over a length of the reference object and the length of the reference object;

determine a first siding measurement based upon the pixel-to-length ratio and a second number of pixels disposed over a first portion of the image of the siding sample corresponding to the first siding measurement; and

identify one or more siding products associated with the first siding measurement.

10. The non-transitory, tangible computer-readable medium of claim 9, further storing instructions that, when executed by the processor, cause the processor to:

determine whether the orientation of the reference object needs to be adjusted such that the edges of the reference object are aligned with edges of the siding sample; and

adjust the orientation of the reference object only when it is determined that the orientation needs to be adjusted.

11. The non-transitory, tangible computer-readable medium of claim 9, further storing instructions that, when executed by the processor, cause the processor to:

rectifying the image of the siding sample so the perspective of the siding sample faces forward if the reference object includes the perspective distortion.

12. The non-transitory, tangible computer-readable medium of claim 9, wherein the instructions to adjust the orientation of the reference object further include instructions, that when executed by the processor, cause the processor to:

adjust the orientation of the reference object and the siding sample in the image such that respective horizontal and vertical edges of each of the reference object and the siding sample are aligned with edges corresponding to a horizontal-vertical plane.

13. The non-transitory, tangible computer-readable medium of claim 9, wherein the instructions to determine the siding measurement further include instructions, that when executed by the processor, cause the processor to:

determine a second siding measurement based upon the pixel-to-length ratio and a third number of pixels disposed over a second portion of the image of the siding sample corresponding to the second siding measurement,

and wherein the instructions to identify the one or more siding products further include instructions, that when executed by the processor, cause the processor to;

identify the one or more siding products associated with the first and the second siding measurement.

14. The non-transitory, tangible computer-readable medium of claim 13, wherein the first siding measurement corresponds to a face size of the siding sample, and wherein the second siding measurement corresponds to a profile size of the siding sample.

15. The non-transitory, tangible computer-readable medium of claim 14, wherein the instructions to identify the one or more siding products further include instructions, that when executed by the processor, cause the processor to:

identify the one or more siding products from siding products stored in the siding product reference database having a face size and a profile size matching the face size and the profile size of the siding sample.

16. The non-transitory, tangible computer-readable medium of claim 9, further storing instructions that, when executed by the processor, cause the processor to:

detect the reference object using at least one of;

a Scale-Invariant Feature Transform (SIFT);

a Speeded Up Robust Features (SURF);

a Radon transform;

or

a Hough transform.

17. A siding product identification system, comprising:

a mobile device configured to (i) adjust an orientation of a reference object within an image of a siding sample to align edges of the reference object with edges of the siding sample, (ii) determine a pixel-to-length ratio representative of a ratio between a first number of pixels disposed over a length of the reference object and the length of the reference object, (iii) facilitate selection by a user of a first portion of the image of the siding sample corresponding to a first siding measurement, and (iv) determine the first siding measurement based upon the pixel-to-length ratio and a second number of pixels disposed over the first portion of the image of the siding sample selected by the user; and

a siding product identification engine configured to identify one or more siding products associated with the first siding measurement.

18. The siding product identification system of claim 17, wherein the mobile device is further configured to:

determine whether the orientation of the reference object needs to be adjusted such that the edges of the reference object are aligned with edges of the siding sample; and

adjust the orientation of the reference object only when it is determined that the orientation needs to be adjusted.

19. The siding product identification system of claim 17, wherein the mobile device is further configured to:

perform image rectification on the image of the siding sample so the perspective of the siding sample faces forward if the reference object includes the perspective distortion.

20. The siding product identification system of claim 17, wherein the mobile device is further configured to:

adjust the orientation of the reference object and the siding sample in the image such that respective horizontal and vertical edges of each of the reference object and the siding sample are aligned with edges corresponding to a horizontal-vertical plane.

21. The siding product identification system of claim 17, wherein the mobile device is further configured to:

determine a second siding measurement based upon the pixel-to-length ratio and a third number of pixels disposed over a second portion of the image of the siding sample corresponding to the second siding measurement, and

wherein the siding product identification engine is further configured to identify the one or more siding products associated with the first and the second siding measurement.

22. The siding product identification system of claim 21, wherein the first siding measurement corresponds to a face size of the siding sample, and wherein the second siding measurement corresponds to a profile size of the siding sample.

23. The siding product identification system of claim 22, wherein the siding product identification engine is further configured to:

receive data representative of the face size and the profile size of the siding sample from the mobile device;

identify the one or more siding products from siding products stored in the siding product reference database having a face size and a profile size matching the face size and the profile size of the siding sample; and

send data representative of the identified one or more siding products to the mobile device.

24. The siding product identification system of claim 17, wherein the mobile device is further configured to detect the reference object using at least one of:

a Scale-Invariant Feature Transform (SIFT);

a Speeded Up Robust Features (SURF);

a Radon transform;

or

a Hough transform.