System and method of measuring distances related to an object

• US 9,230,339 B2
• Filed: 07/01/2014
• Issued: 01/05/2016
• Est. Priority Date: 01/07/2013
• Status: Active Grant

• Current Assignee: WexEnergy Innovations LLC
• Original Assignee: WexEnergy Innovations LLC
• Inventors: Wexler, Ronald Myron, Spence, John Patrick, Luo, Jiebo
• Primary Examiner(s): Couso, Yon
• Application Number:
  US14/320,973
• Publication Number:
  US 20140314276A1
• Time in Patent Office: 553 Days
• Field of Search: 382/103
• US Class Current: 1/1
• CPC Class Codes: G01B 11/022 by means of tv-camera scanning
• CPC Class Codes: G01C 11/04 Interpretation of pictures
• CPC Class Codes: G06T 2207/30208 Marker matrix
• CPC Class Codes: G06T 3/04 Context-preserving transformations, e.g. by using an importance map panospheric to cylindrical image transformations G06T3/12
• CPC Class Codes: G06T 7/62 of area, perimeter, diameter or volume

Abstract

A system and method for measuring distances related to a target object depicted in an image and the construction and delivery of supplemental window materials for fenestration. A digital image is obtained that contains a target object dimension and a reference object dimension in the same plane. The digital image may contain a target object dimension identified by an ancillary object and a reference object dimension in different planes. Fiducial patterns on the reference and optional ancillary objects are used that are recognized by an image analysis algorithm. Information regarding a target object and its immediate surroundings is provided to an automated or semi-automated measurement process, design and manufacturing system such that customized parts are provided to end users. The digital image contains a reference object having a reference dimension and calculating a constraint dimension from the digital image based on a reference dimension. The custom part is then designed and manufactured based on a calculated constraint dimension.

Claims

1. A computer implemented method of estimating at least one dimension of a target object within a digital image which includes a reference object having a fiducial pattern printed thereon placed substantially in a plane of the target object, the method comprising:

obtaining a digital image, on a computer, containing the target object and the reference object;

locating, on a computer, the reference object in the digital image by searching for the fiducial pattern, said reference object having one or more known linear dimensions viewable in said digital image;

determining, on a computer, pixel dimensions of said reference object using edge detection image processing to identify pixel locations bounding the reference object;

calculating, on a computer, a pixel scale factor based on at least one reference object pixel dimension in the digital image and at least one known linear physical dimension of the reference object;

locating, on a computer, the target object in the digital image; and

calculating, on a computer, the at least one dimension of the target object based on the pixel scale factor.

2. The method according to claim 1, further comprising providing feedback to a user if the reference object fiducial cannot be found in the digital image.

3. The method according to claim 1, further comprising providing feedback to a user to indicate insufficient contrast between a window pane background and the reference object.

4. The method according to claim 1, further comprising providing feedback to a user that includes one or more suggestions for scene adjustment to improve detection of the reference object.

5. The method according to claim 1, further comprising applying a perspective transform to the digital image.

6. The method according to claim 5, wherein said perspective transform comprises a balanced normalized center-preserving transform.

7. The method according to claim 1, wherein said target object comprises a window.

8. The method according to claim 7, further comprising locating window pane edge contours utilizing the location of the reference object.

9. The method according to claim 7, wherein the digital image includes one or more ancillary objects having a respective measurement point demarcating feature and the at least one dimension is calculated using window pane contour dimensions, one or more ancillary object feature demarcated measurement points relative to the window pane contour dimensions and symmetry of one or more window related elements.

10. The method according to claim 1, wherein the digital image includes one or more ancillary objects each having a respective measurement point demarcating feature.

11. A computer implemented method of estimating at least one dimension of a window within a digital image which includes a reference object having a fiducial pattern printed thereon placed substantially in a plane of the window, the method comprising:

obtaining a digital image, on a computer, containing the window and the reference object;

applying, on a computer, a perspective transform to the digital image;

locating, on a computer, said reference object in the digital image by searching for said fiducial pattern, said reference object having one or more known linear dimensions viewable in said digital image;

determining, on a computer, pixel dimensions of said reference object;

calculating, on a computer, a pixel scale factor based on at least one reference object pixel dimension in the digital image and at least one known linear physical dimension of the reference object;

locating, on a computer, the window in the digital image;

calculating, on a computer, the at least one dimension of the window based on the pixel scale factor.

12. The method according to claim 11, wherein end user information is encoded on the reference object.

13. The method according to claim 11, wherein metadata is encoded on the reference object.

14. The method according to claim 11, wherein the digital image includes one or more ancillary objects having a respective measurement point demarcating feature and the at least one dimension of the window is calculated using window pane contour dimensions, one or more ancillary object feature demarcated measurement points relative to the window pane contour and symmetry of one or more window related elements.

15. A method of estimating at least one dimension of a target object within a digital image which includes a reference object having a reference fiducial pattern printed thereon and one or more ancillary objects each having a respective measurement point demarcating feature for aiding in determining the dimensions of the target object and having a respective ancillary fiducial pattern printed thereon, the method comprising:

obtaining a digital image, on a computer, containing the target object, reference object and one or more ancillary objects;

applying, on a computer, a perspective transform to the digital image;

locating, on a computer, the reference object in the digital image by searching for said reference fiducial pattern, said reference object having one or more known linear dimensions viewable in said digital image;

determining, on a computer, pixel dimensions of said reference object;

calculating, on a computer, a reference pixel scale factor based on at least one reference object pixel dimension in the digital image and at least one known linear physical dimension of the reference object;

locating, on a computer, the one or more ancillary objects in the digital image by searching for said respective ancillary fiducial pattern;

locating, on a computer, the target object in the digital image; and

calculating, on a computer, the at least one dimension of the target object utilizing the pixel scale factor and one or more respective measurement point demarcating features.

16. The method according to claim 15, wherein both said reference object and said ancillary object are in the same plane.

17. The method according to claim 15, wherein said reference object and said ancillary object are in different planes and an ancillary pixel scale factor is calculated based on both measured and known dimensions of the one or more ancillary objects or ancillary fiducial patterns on the one or more ancillary objects.

18. The method according to claim 17, further comprising determining the distance between the two planes based on said reference pixel scale factor and said ancillary pixel scale factor.

19. The method according to claim 15, wherein said one or more ancillary objects function to demarcate one or more measurement points.

20. The method according to claim 15, wherein said one or more ancillary objects function to aid in determining a top edge of said target object in the event a window treatment is present on said target object.

21. The method according to claim 15, wherein said one or more ancillary objects function to determine a depth offset between planes if the target object consists of more than one plane.

22. The method according to claim 15, wherein end user information is encoded on the reference or ancillary fiducial patterns.

23. The method according to claim 15, wherein metadata is encoded on the reference or ancillary fiducial patterns.

24. The method according to claim 15, further comprising locating window pane edge contours utilizing the location of the reference object.

25. The method according to claim 15, wherein the at least one dimension of a window is calculated using window pane contour dimensions, one or more fiducial demarcated measurement points relative to the window pane contour and symmetry of one or more window related elements.

26. The method according to claim 15, further comprising locating the camera position in the digital image and using said position to aid in calculating said at least one dimension.

27. The method according to claim 15, wherein said perspective transform comprises a balanced normalized center-preserving transform.

28. A computer program product for estimating at least one dimension of a target object within a digital image which includes a reference object having a fiducial pattern printed thereon placed substantially in a plane of the target object, the computer program product comprising:

a non-transitory, tangible computer usable storage medium having computer usable code embodied therewith, the computer usable program code comprising;

computer usable code configured for obtaining a digital image containing the target object and the reference object;

computer usable code configured for locating the reference object in the digital image by searching for the fiducial pattern, said reference object having one or more known linear dimensions viewable in said digital image;

computer usable code configured for determining pixel dimensions of said reference object using edge detection image processing to identify pixel locations bounding the reference object;

computer usable code configured for calculating a pixel scale factor based on at least one reference object pixel dimension in the digital image and at least one known linear physical dimension of the reference object;

computer usable code configured for locating the target object in the digital image; and

computer usable code configured for calculating the at least one dimension of the target object based on the pixel scale factor.