Automated 3-D modeling of shoe parts

• US 8,849,620 B2
• Filed: 11/18/2011
• Issued: 09/30/2014
• Est. Priority Date: 11/18/2011
• Status: Active Grant

• Current Assignee: Nike, Inc.
• Original Assignee: Nike, Inc.
• Inventors: Regan, Patrick Conall, Chang, Chih-Chi, Jean, Ming-Feng
• Primary Examiner(s): Shah, Kamini S
• Assistant Examiner(s): Healey, Michael P
• Application Number:
  US13/299,827
• Publication Number:
  US 20130132038A1
• Time in Patent Office: 1,047 Days
• US Class Current: 703/1
• CPC Class Codes: A43D 1/08 Measuring devices for shoe parts
• CPC Class Codes: A43D 2200/60 Computer aided manufacture of footwear, e.g. CAD or CAM
• CPC Class Codes: A43D 25/06 Devices for gluing soles on shoe bottoms A43D25/18, A43D25/20 take precedence
• CPC Class Codes: A43D 8/00 Machines for cutting, ornamenting, marking or otherwise working up shoe part blanks pulling-over or lasting A43D9/00 - A43D23/00; making or fastening soles, heels or welts A43D25/00 - A43D83/00
• CPC Class Codes: A43D 95/00 Shoe-finishing machines
• CPC Class Codes: B25J 9/1684 Tracking a line or surface by means of sensors
• CPC Class Codes: G01B 11/02 for measuring length, width or thickness G01B11/08 takes precedence
• CPC Class Codes: G01B 11/03 by measuring coordinates of points
• CPC Class Codes: G01B 11/24 for measuring contours or curvatures
• CPC Class Codes: G01B 11/2518 Projection by scanning of the object
• CPC Class Codes: G01B 11/2522 the position of the object changing and being recorded
• CPC Class Codes: G05B 2219/37205 Compare measured, vision data with computer model, cad data
• CPC Class Codes: G05B 2219/37555 Camera detects orientation, position workpiece, points of workpiece
• CPC Class Codes: G05B 2219/39393 Camera detects projected image, compare with reference image, position end effector
• CPC Class Codes: G06F 30/00 Computer-aided design [CAD]
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 19/00 Manipulating 3D models or images for computer graphics
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/10144 Varying exposure
• CPC Class Codes: G06T 2207/30108 : Industrial image inspection
• CPC Class Codes: G06T 7/521 : from laser ranging, e.g. using interferometry; from the projection of structured light
• CPC Class Codes: G06T 7/543 : from line drawings

Abstract

Manufacturing of a shoe is enhanced by creating 3-D models of shoe parts. For example, a laser beam may be projected onto a shoe-part surface, such that a projected laser line appears on the shoe part. An image of the projected laser line may be analyzed to determine coordinate information, which may be converted into geometric coordinate values usable to create a 3-D model of the shoe part. Once a 3-D model is known and is converted to a coordinate system recognized by shoe-manufacturing tools, certain manufacturing steps may be automated.

Claims

1. A method for analyzing scans of a shoe part to generate dimension data, which is useable to model three-dimensional (3-D) features of the shoe part, the method comprising:

projecting a first laser beam onto a shoe-part surface of the shoe part that is comprised of a surface topography, such that a first projected laser line extends across a section of the shoe-part surface;

recording a first image of the first projected laser line using both a first camera having a black-shoe-part exposure setting and a second camera having a white-shoe-part exposure setting, wherein the first image comprises a representation of the first projected laser line and comprises an extraneous depiction of light;

determining coordinate points that define the representation of the first projected laser line as depicted in the first image, wherein a filtering method is applied to the coordinate points to remove one or more noisy coordinate points defining the light that is extraneously depicted;

combining the coordinate points that define the representation of the first projected laser line with a first plurality of other coordinate points, which are derived from first additional images recorded when the first laser beam is projected onto other sections of the shoe-part surface, thereby compiling a first set of coordinate points that represent the surface topography; and

converting the first set of coordinate points into geometric coordinate points that represent a 3-D model of the surface topography.

2. The method of claim 1, wherein the shoe part comprises a midsole portion comprised of the shoe-part surface and wherein the first set of coordinate points maps a concave surface topography.

3. The method of claim 2, wherein the shoe part further comprises a lasted shoe upper comprised of the shoe-part surface in combination with the midsole portion and wherein the first set of coordinate points maps a partially convex surface topography.

4. The method of claim 3 further comprising, rotating the lasted shoe upper in combination with the midsole portion on a turntable when the first image and the additional images are recorded, such that the section and the other sections span a 360 degree view of the lasted shoe upper in combination with the midsole portion.

5. The method of claim 3 further comprising,

projecting a second laser beam onto the shoe-part surface, such that a second projected laser line extends across the section of the shoe-part surface, wherein the first projected laser line extends across a first portion of the section and the second projected laser line extends across a second portion of the section that overlaps the first portion;

recording a second image of the second projected laser line, wherein the second image comprises a representation of the second projected laser line;

determining coordinate points that define the representation of the second projected laser line as depicted in the second image;

combining the coordinate points that define the representation of the second projected laser line with a second plurality of other coordinate points which are derived from second additional images recorded when the second laser beam is projected onto said other sections of the shoe-part surface, thereby compiling a second set of coordinate points; and

combining the second set of coordinate points with the first set of coordinate points to generate a third set of coordinate points that represent the surface topography.

6. The method of claim 1,

wherein the first set of coordinate points comprises a plurality of ordered sets, and

wherein one element of each ordered set of the plurality of ordered sets comprises a height element and another element of the each ordered set of the plurality of ordered sets comprises a width element.

7. The method of claim 6, wherein the each ordered set further comprises a depth element.

8. The method of claim 7, wherein the depth element is based on a speed at which the shoe part is moved when the first image and the additional images are recorded and a number of images recorded in a given amount of time.

9. The method of claim 6,

wherein at least two sets of the plurality of ordered sets comprise a same width-element value, and

wherein a set of the at least two sets that comprises at least one of a higher or a lower height-element value is removed from the plurality of ordered sets.

10. The method of claim 1,

wherein the first camera and the second camera are positioned side-by-side.

11. A method for analyzing scans of a shoe part to generate dimension data, which is useable to model three-dimensional (3-D) features of the shoe part, the method comprising:

attaching a shoe bottom onto a lasted shoe upper, such that a terminal edge of the shoe bottom encircles the lasted shoe upper;

projecting a laser beam onto the shoe bottom and the lasted shoe upper, such that a first segment of a projected laser line extends on the shoe bottom and a second segment of the projected laser line extends on the lasted shoe upper;

recording an image of the projected laser line that depicts a first-segment representation and a second-segment representation, wherein an interface region between the first-segment representation and the second-segment representation represents a position of the terminal edge;

identifying a coordinate point of the interface region that defines a position of the interface region as depicted in the image; and

converting the coordinate point to a geometric coordinate point of the lasted shoe upper, wherein the geometric coordinate point is deemed a bite point that represents a position on the lasted shoe upper that is aligned with a portion of the terminal edge.

12. The method of claim 11, wherein a plurality of images is recorded as the lasted shoe upper is rotated by 360 degrees.

13. The method of claim 12, wherein a respective coordinate point is derived from each image of the plurality of images.

14. The method of claim 13, wherein each respective coordinate point is converted to a respective geometric coordinate point of the lasted shoe upper, and wherein a plurality of geometric coordinate points that are converted from respective coordinate points are deemed a bite line.

15. A system that analyzes scans of a shoe part to generate dimension data, which is useable to model three-dimensional (3-D) features of the shoe part, the system comprising:

a shoe-part moving apparatus that retains the shoe part and moves the shoe part through a range of positions, wherein the shoe part comprises a surface topography;

a laser that projects a first laser beam onto a section of the shoe part as the shoe part is moved to a position of the range of positions, such that a first projected laser line extends across the section;

a first camera having a black-shoe-part exposure setting that records a first image of the first projected laser line, wherein the first image depicts a representation of the first projected laser line extending across the section;

a second camera having a white-shoe-part exposure setting that records a second image of the first projected laser line, wherein the second image depicts the representation of the first projected laser line extending across the section; and

computer storage media having stored thereon computer-executable instructions that, when executed by a computing device, cause the computing device to;

(1) derive coordinate points from the first image and the second image that define the representation of the first projected laser line as depicted in the first image and the second image;

(2) combine the coordinate points with a plurality of other coordinate points, which are derived from additional images recorded when the first laser beam is projected onto other sections of the shoe part, thereby compiling a combination of coordinate points that represent the surface topography; and

(3) convert the combination of coordinate points into geometric coordinate points that represent a 3-D model of the surface topography.

16. The system of claim 15, wherein the shoe-part moving apparatus comprises a conveyor and wherein the range of positions is spaced along a straight axis.

17. The system of claim 16 further comprising,

a second laser projecting a second laser beam onto the shoe part;

and

a third camera that records images of a second projected laser line created on the shoe part by the second laser beam.

18. The system of claim 17, wherein the first laser beam and the second laser beam overlap one another, thereby creating an overlapping curtain, and wherein the overlapping curtain is substantially perpendicular to a belt of the conveyor.

19. The system of claim 15, wherein the shoe-part moving apparatus comprises a turntable apparatus that rotates the shoe part by 360 degrees.

20. The system of claim 15 wherein the first camera and the second camera are positioned adjacent to each other.