System for 3D Clothing Model Creation

• US 10,127,717 B2
• Filed: 02/17/2017
• Issued: 11/13/2018
• Est. Priority Date: 02/16/2016
• Status: Active Grant

• Current Assignee: Ohzone Inc.
• Original Assignee: Ohzone Inc.
• Inventors: Tepmongkol, Warangkana, Myers, John R., Bunce, Richard W., Acken, Kevin P
• Primary Examiner(s): Hoang, Phi
• Application Number:
  US15/436,481
• Publication Number:
  US 20170287210A1
• Time in Patent Office: 634 Days
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20182 Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
• CPC Class Codes: G06T 2207/30124 Fabrics; Textile; Paper
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2210/16 Cloth
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/337 involving reference images or patches
• CPC Class Codes: G06T 7/579 from motion
• CPC Class Codes: H04N 13/271 wherein the generated image signals comprise depth maps or disparity maps
• CPC Class Codes: H04N 13/282 for generating image signals corresponding to three or more geometrical viewpoints, e.g. multi-view systems

Abstract

A system for creating a model of an article of clothing or other wearable, the system includes a mannequin or other model of at least a portion of a human form; a sensing device configured to scan the mannequin without the wearable to generate a first scan information and configured to scan the surface of the wearable on the mannequin to generate a second scan information; a processor communicatively coupled to the sensing device to receive the first and second scan information, the processor configured to: generate point clouds using the scan information; aligning the point clouds; generating a plurality of slices along at least one longitudinal axis through the point clouds, each slice having a centroid along a corresponding longitudinal axis; and generating a table having a plurality of entries each representing a distance between corresponding vertices for the pair of point clouds; the table representing the wearable.

Claims

1. A system for creating a model of a wearable having a surface, the system comprising:

an object comprising a portion of a human form, the portion of the human form having a body surface;

a sensing device configured to scan the body surface of the object without the wearable to generate a first scan information and configured to scan the surface of the wearable on the portion of the human form to generate a second scan information;

a processor communicatively coupled to the sensing device to receive the first and second scan information, the processor configured to;

(a) generate a first point cloud using the first scan information and a second point cloud using the second scan information;

(b) align the first and second point clouds;

(c) generate a plurality of slices along at least one longitudinal axis through the first and second point clouds, each slice having a centroid along a corresponding longitudinal axis;

(d) generate a table having a plurality of entries each representing a distance between corresponding vertices for the first and second point clouds; and

a storage means for storing the table representing the wearable.

2. The system of claim 1 wherein the sensing device comprises a three-dimension depth sensor.

3. The system of claim 1 wherein the sensing device comprises a camera.

4. The system of claim 1 wherein the processor is configured to align the first and second point clouds by identifying at least one feature of the human form in both the first and second point clouds.

5. The system of claim 4 wherein the at least one feature comprises at least one of a neck, shoulder, armpit, bust and crotch.

6. The system of claim 1 wherein the processor is configured to align the first and second point clouds by applying a smoothing filter to the centroid positioning along each longitudinal axis.

7. The system of claim 1 wherein the processor is further configured to extract from the first scan information, a color and a relative position for each point of the first point cloud;

and extract from the second scan information, a color and a relative position for each point of the second point cloud.

8. The system of claim 1 wherein the sensing device is in a fixed position relative to the portion of the human form to capture the first and second scan information.

9. The system of claim 1 wherein the sensing device is moved relative to the portion of the human form to capture the first and second scan information.

10. The system of claim 1 wherein the portion of the human form is moved relative to the sensing device to capture the first and second scan information.

11. The system of claim 1 wherein the processor is further configured to identify at least one physical cue in both the first and second point clouds, wherein the first and second point clouds are aligned using the physical cue identified in each of the first and second point clouds.

12. A system for creating a model of a wearable having a surface, the system comprising:

an object comprising a portion of a human form, the portion of the human form having a body surface;

a sensing device configured to scan the body surface of the object without the wearable to generate a first scan information and configured to scan the surface of the wearable on the portion of the human form to generate a second scan information;

a processor communicatively coupled to the sensing device to receive the first and second scan information, the processor configured to;

(a) generate a first point cloud using the first scan information and a second point cloud using the second scan information;

(b) align the first and second point clouds;

(c) generate a plurality of slices along at least one longitudinal axis through the first and second point clouds, each slice having a centroid along a corresponding longitudinal axis;

(d) apply a smoothing filter to the centroid positioning along at least one longitudinal axis; and

(e) generate a table having a plurality of entries each representing a distance between corresponding vertices for the first and second point clouds; and

a storage means for storing the table representing the wearable.

13. The system of claim 12 wherein the sensing device comprises a three-dimension depth sensor.

14. The system of claim 12 wherein the sensing device comprises a camera.

15. The system of claim 12 wherein the processor is configured to align the first and second point clouds by identifying at least one feature of the human form in both the first and second point clouds.

16. The system of claim 15 wherein the at least one feature comprises at least one of a neck, shoulder, armpit, bust and crotch.

17. The system of claim 12 wherein the processor is further configured to extract from the first scan information, a color and a relative position for each point of the first point cloud;

and extract from the second scan information, a color and a relative position for each point of the second point cloud.

18. The system of claim 12 wherein the sensing device is in a fixed position relative to the portion of the human form to capture the first and second scan information.

19. The system of claim 12 wherein the sensing device is moved relative to the portion of the human form to capture the first and second scan information.

20. The system of claim 12 wherein the portion of the human form is moved relative to the sensing device to capture the first and second scan information.

21. The system of claim 12 wherein the processor is further configured to identify at least one physical cue in both the first and second point clouds, wherein the first and second point clouds are aligned using the physical cue identified in each of the first and second point clouds.

22. A computer-implemented method of creating a model of a wearable having a surface, the method comprising:

receiving a first point cloud representing at least a portion of a human form, the portion of the human form having a body surface;

receiving a second point cloud representing at least a portion of a human form dressed with the wearable;

aligning the first and second point clouds;

generating slices of the first and second point clouds substantially along the longitudinal axes of the human form, each slice having a centroid along a corresponding longitudinal axis; and

generating a table comprising distances between corresponding points in the first and second point cloud, wherein the table representing the wearable.

23. The computer-implemented method of claim 22 further comprising applying a smoothing filter to the centroid positioning along at least one longitudinal axis.