Method and apparatus for estimating body shape

• US 10,002,460 B2
• Filed: 10/16/2015
• Issued: 06/19/2018
• Est. Priority Date: 08/15/2008
• Status: Active Grant

• Current Assignee: Brown University
• Original Assignee: Brown University
• Inventors: Black, Michael J., Balan, Alexandru O., Weiss, Alexander W., Sigal, Leonid, Loper, Matthew M., St. Clair, Timothy S.
• Primary Examiner(s): Liew, Alex
• Application Number:
  US14/885,333
• Publication Number:
  US 20160203361A1
• Time in Patent Office: 977 Days
• Field of Search: 382115-118
• CPC Class Codes: G06F 18/2321 using statistics or function optimisation, e.g. modelling of probability density functions
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/75 involving models
• CPC Class Codes: G06T 7/77 using statistical methods
• CPC Class Codes: G06V 10/763 Non-hierarchical techniques, e.g. based on statistics of modelling distributions
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appear in minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.

Claims

1. A method comprising:

generating, via a processor and based on a first parametric body model of a first individual, a first set of attributes that at least one of (1) identify one or more characteristics of the first individual and (2) are derived from a shape of the first individual;

generating, via the processor and based on two or more parametric body models stored in a memory, of two or more individuals, two or more sets of attributes, wherein each set of the two or more sets of attributes at least one of (1) identifies one or more characteristics for one of the two or more individuals and (2) is derived from a shape of one of the two or more individuals; and

determining, via the processor and based on the first set of attributes and the two or more sets of attributes, a set of similarity measures between the first set of attributes and each of the two or more sets of attributes.

2. The method of claim 1, wherein the first set of attributes and the two or more sets of attributes comprise one or more of an age, height, fitness level and a clothing size of a respective one of the first individual and the two or more individuals.

3. The method of claim 1, wherein each of the first parametric body model and the two or more parametric body models has a plurality of associated vertex locations.

4. The method of claim 3, wherein each of the first parametric body model and the two or more parametric body models defines a respective mesh, and wherein the respective mesh of the first parametric body model and each of the two or more parametric body models are aligned.

5. The method of claim 3, wherein the set of similarity measures comprises determining distances between selected ones of the associated vertex locations of the first parametric body model and the two or more parametric body models.

6. The method of claim 1, further comprising:

generating, based on the set of similarity measures, a ranking of similarities between the first set of attributes of the first individual and the two or more sets of attributes of the two or more individuals.

7. The method of claim 1, further comprising estimating at least one measurement associated with a body of the first individual based on the set of similarity measures between the first set of attributes and the two or more sets of attributes.

8. The method of claim 7, wherein the estimating the at least one measurement associated with the body of the first individual is performed in association with a purchase of clothing for the first individual.

9. The method of claim 8, further comprising generating a recommendation for the first individual pertaining to at least one of a clothing attribute, a body measurement attribute, or a body shape attribute based on the at least one measurement.

10. The method of claim 9, further comprising executing an application that uses the recommendation in a decisional process, the application comprising at least one of a clothing software application, a film application, a forensic video application, a fitness application, and a health application.

11. A system comprising:

a processor; and

a computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform operations comprising;

obtaining a first parametric body model representing a body of a first individual;

generating, based on the first parametric body model, a first set of attributes that at least one of (1) identify one or more characteristics of the first individual and (2) are derived from a shape of the first individual;

generating, based on two or more parametric body models, stored in a memory, of two or more individuals, two or more sets of attributes, wherein each of the two or more sets of attributes at least one of (1) identifies one or more characteristics for one of the two or more individuals and (2) is derived from a shape of one of the two or more individuals; and

determining, based on the first set of attributes and the two or more sets of attributes, a set of similarity measures between the first set of attributes and each of the two or more sets of attributes.

12. The system of claim 11, wherein the first set of attributes and the two or more sets of attributes comprise one or more of an age, height, fitness level and a clothing size of a respective one of the first individual and the two or more individuals.

13. The system of claim 11, wherein each of the first parametric body model and the two or more parametric body models has a plurality of associated vertex locations.

14. The system of claim 13, wherein each of the first parametric body model and the two or more parametric body models defines a respective mesh, and wherein the respective mesh of the first parametric body model and each of the two or more parametric body models are aligned.

15. The system of claim 13, wherein the set of similarity measures comprises determining distances between selected ones of the associated vertex locations of the first parametric body model and the two or more parametric body models.

16. The system of claim 11, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising:

generating, based on the set of similarity measures, a ranking of similarities between the first set of attributes of the first individual and the two or more sets of attributes of the two or more individuals.

17. A computer-readable storage device having stored therein instructions which, when executed by a processor, cause the processor to perform operations comprising:

based on a first parametric body model of a first individual, generating a first set of attributes that at least one of (1) identify one or more characteristics of the first individual and (2) are derived from a shape of the first individual;

generating, based on two or more parametric body models, stored in a memory, of two or more individuals, two or more sets of attributes, wherein each set of the two or more sets of attributes at least one of (1) identifies one or more characteristics for one of the two or more individuals and (2) is derived from a shape of one of the two or more individuals; and

determining, based on the first set of attributes and the two or more sets of attributes, a set of similarity measures between the first set of attributes and each of the two or more sets of attributes.

18. The computer-readable storage device of claim 17, storing additional instructions which, when executed by the processor, cause the processor to perform operations further comprising estimating at least one measurement associated with a body of the first individual based on the set of similarity measures between the first set of attributes and the two or more sets of attributes, wherein the estimating of the at least one measurement associated with the body of the first individual is performed in association with a purchase of clothing for the first individual.

19. The computer-readable storage device of claim 17, wherein

each of the first parametric body model and the two or more parametric body models has a plurality of associated vertex locations and defines a respective mesh,

wherein respective meshes of the first parametric body model and each of the two or more parametric body models are aligned, and

the determining the set of similarity measures comprises determining distances between selected ones of the associated vertex locations of the first parametric body model and each of the two or more parametric body models.

20. The computer-readable storage device of claim 17, wherein the computer-readable storage device stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising generating, for the first individual, a recommendation pertaining to at least one of a clothing attribute, a body measurement attribute, or a body shape attribute based on the set of similarity measures.