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

• US 9,536,301 B1
• Filed: 12/29/2015
• Issued: 01/03/2017
• 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:
  US14/982,074
• Time in Patent Office: 371 Days
• Field of Search: 348/137
• US Class Current: 1/1
• 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 mobile computing device, comprising:

a memory configured to store computer-readable instructions; and

a central processing unit (CPU) configured to;

execute the computer-readable instructions stored in the memory to analyze an image of a siding sample including a reference object;

selectively align edges of the reference object within the image of the siding sample with edges of the siding sample when it is determined that an orientation of the reference object needs to be adjusted;

measure a dimension of the reference object in terms of pixels, the measurement being one of (i) the dimension of the reference object after being aligned, if the orientation of the reference object needs to be adjusted, or (ii) the dimension of the reference object without being aligned, if the orientation of the reference object does not need to be adjusted;

measure a first dimension of the siding sample based upon the dimension of the reference object in terms of pixels and a first number of pixels spanned by the first dimension of the siding sample within the image of the siding sample; and

identify a siding product associated with the first dimension of the siding sample.

2. The mobile computing device of claim 1, wherein the CPU is further configured to determine that the orientation of the reference object needs to be adjusted when the reference object is not aligned parallel with a portion of the siding sample within the image of the siding sample.

3. The mobile computing device of claim 1, wherein the CPU is further configured to rectify the image of the siding sample so the perspective of the siding sample faces forward if the reference object includes perspective distortion.

4. The mobile computing device of claim 1, wherein the CPU is further configured to measure a second dimension of the siding sample based upon the dimension of the reference object in terms of pixels and a second number of pixels spanned by the second dimension of the siding sample within the image of the siding sample, and to identify the siding product based upon the first and second dimensions of the siding sample.

5. The mobile computing device of claim 4, wherein:

the first dimension of the siding sample corresponds to a face dimension,

the second dimension of the siding sample corresponds to a profile dimension, and

the CPU is further configured to identify the siding product stored in a siding product reference database having a face dimension and a profile dimension matching the first dimension and the second dimension of the siding sample, respectively.

6. The mobile computing device of claim 1, wherein the CPU 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.

7. A siding identification engine, comprising:

a memory configured to store computer-readable instructions; and

a central processing unit (CPU) configured to execute the computer-readable instructions stored in the memory to identify a siding product by;

receiving an image of a siding sample including a reference object from a mobile computing device;

selectively aligning edges of the reference object within the image of the siding sample with edges of the siding sample when it is determined that an orientation of the reference object needs to be adjusted;

measuring a dimension of the reference object in terms of pixels, the measurement being one of (i) the dimension of the reference object after being aligned, if the orientation of the reference object needs to be adjusted, or (ii) the dimension of the reference object without being aligned, if the orientation of the reference object does not need to be adjusted;

measuring a first dimension of the siding sample based upon the dimension of the reference object in terms of pixels and a first number of pixels spanned by the first dimension of the siding sample within the image of the siding sample; and

matching the first dimension of the siding sample to a stored first siding dimension stored in a siding product reference database to identify the siding product that corresponds to the siding sample.

8. The siding identification engine of claim 7, wherein the CPU is further configured to cause the siding identification engine to wirelessly communicate the identified siding product associated with the stored first siding dimension to the mobile computing device via a network.

9. The siding identification engine of claim 7, wherein the CPU is further configured to determine that the orientation of the reference object needs to be adjusted when the reference object is not aligned parallel with a portion of the siding sample within the image of the siding sample.

10. The siding identification engine of claim 7, wherein the CPU is further configured to rectify the image of the siding sample so the perspective of the siding sample faces forward if the reference object includes perspective distortion.

11. The siding identification engine of claim 7, wherein the CPU is further configured to measure a second siding sample dimension based upon the dimension of the reference object in terms of pixels and a second number of pixels spanned by the second siding sample dimension within the image of the siding sample, and to identify the siding product by matching the first and second dimensions of the siding sample to the stored first siding dimension and a stored second siding dimension, respectively, that are stored in the siding product reference database.

12. The siding identification engine of claim 11, wherein:

the first dimension of the siding sample corresponds to a face dimension,

the second dimension of the siding sample corresponds to a profile dimension, and

the CPU is further configured to identify the siding product stored in the siding product reference database having a face dimension and a profile dimension matching the first dimension and the second dimension of the siding sample, respectively.

13. The siding identification engine of claim 7, wherein the CPU 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.

14. A siding identification system, comprising:

a mobile computing device configured to transmit data representative of an image of a siding sample including a reference object; and

an external computing device configured to;

receive the image of the siding sample including the reference object;

selectively align edges of the reference object within the image of the siding sample with edges of the siding sample when it is determined that an orientation of the reference object needs to be adjusted;

measure a dimension of the reference object in terms of pixels, the measurement being one of (i) the dimension of the reference object after being aligned, if the orientation of the reference object needs to be adjusted, or (ii) the dimension of the reference object without being aligned, if the orientation of the reference object does not need to be adjusted;

measure a first dimension of the siding sample based upon the dimension of the reference object in terms of pixels and a first number of pixels spanned by the first dimension of the siding sample within the image of the siding sample; and

match the first dimension of the siding sample to a stored first siding dimension stored in a siding product reference database to identify a siding product that corresponds to the siding sample.

15. The siding identification system of claim 14, wherein the external computing device is further configured to wirelessly communicate the identified siding product associated with the stored first siding dimension to the mobile computing device via a network.

16. The siding identification system of claim 14, wherein the external computing device is further configured to determine that the orientation of the reference object needs to be adjusted when the reference object is not aligned parallel with a portion of the siding sample within the image of the siding sample.

17. The siding identification system of claim 14, wherein the external computing device is further configured to rectify the image of the siding sample so the perspective of the siding sample faces forward if the reference object includes perspective distortion.

18. The siding identification system of claim 14, wherein the external computing device is further configured to measure a second siding sample dimension based upon the dimension of the reference object in terms of pixels and a second number of pixels spanned by the second siding sample dimension within the image of the siding sample, and to identify the siding product by matching the first and second dimensions of the siding sample to the stored first siding dimension and a stored second siding dimension, respectively, that are stored in the siding product reference database.

19. The siding identification system of claim 18, wherein:

the first dimension of the siding sample corresponds to a face dimension,

the second dimension of the siding sample corresponds to a profile dimension, and

the external computing device is further configured to identify the siding product stored in the siding product reference database having a face dimension and a profile dimension matching the first dimension and the second dimension of the siding sample, respectively.

20. The siding identification system of claim 14, wherein the external computing device engine 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.