US 11,232,629 B1Granted

Two-dimensional image collection for three-dimensional body composition modeling

AssigneeAmazon Technologies, Inc.

InventorsDavid Lawrence Seymore, Prakash Ramu, Aneeb Qureshi, Ita Lifshitz, Anta Imata Safo, Megan Heffernan

Life of this patent

Estimating the term…

Loading patent…

Abstract

Described are systems and method directed to generation of a dimensionally accurate three-dimensional (“3D”) body model of a body, such as a human body, based on two-dimensional (“2D”) images of that body. A user may use a 2D camera, such as a digital camera typically included in many of today's portable devices (e.g., cell phones, tablets, laptops, etc.) and obtain a series of 2D body images of their body from different directions with respect to the camera. The 2D body images may then be used to generate a plurality of predicted body parameters corresponding to the body represented in the 2D body images. Those predicted body parameters may then be further processed to generate a dimensionally accurate 3D model of the body of the user.

Claims20

Dependent claims

A computer-implemented method, comprising:

receiving, with an application executing on a portable device, a first plurality of two-dimensional (“2D”) body images generated by a camera of the portable device;
processing, with the application, at least one of the first plurality of 2D body images to at least:
determine body point locations for each of a plurality of body points of a body represented in at least one of the first plurality of 2D body images;
determine, based at least in part on two or more of the body point locations, a first angle of a body part of the body;
and
determine that the first angle of the body part is not within a defined range;
presenting, through at least one output of the portable device, a request that the body part be repositioned;
subsequent to presenting the request:
processing at least a second 2D body image of a second plurality of 2D body images to determine second body point locations for each of the plurality of body points of the body;
determining, based at least in part on two or more of the second body point locations, a second angle of the body part;
determining that the second angle of the body part is within the defined range;
and
based at least in part on determining that the second angle of the body part is within the defined range, determining that the body is positioned in a defined pose;
subsequent to determining that the body is positioned in the defined pose:
receiving, with the application, a third plurality of 2D body images generated by the camera;
and
processing, with the application, at least one of the third plurality of 2D body images to determine a body direction of the body;
in response to determining the body direction of the body:
receiving, with the application, a fourth plurality of 2D body images generated by the camera;
and
selecting a first image from the fourth plurality of 2D body images as a 2D body direction image of the body in the body direction;
sending, from the application and from the portable device, the 2D body direction image;
subsequent to sending the 2D body direction image, receiving, with the application, three-dimensional (“3D”) body model parameters and a body measurement, wherein the 3D body model parameters and the body measurement are determined based at least in part on the 2D body direction image;
rendering, on the portable device and based at least in part on the 3D body model parameters, a 3D body model representative of the body;
and
presenting, with the application and via a display of the portable device, the 3D body model and the body measurement.

23 more elements

A system, comprising:

a remote computing resource operable to at least:
receive one or more two-dimensional (“2D”) body direction images of a body;
and
generate, based at least in part on the one or more 2D body direction images, three-dimensional (“3D”) body model parameters corresponding to the body;
and
an application stored on a memory of a portable device that includes an imaging element, wherein the application when executed by one or more processors of the portable device, cause the one or more processors to at least:
process one or more first two-dimensional (“2D”) body images generated by the imaging element to at least:
determine body point locations for each of a plurality of body points of a body represented in the one or more first 2D body images;
determine, based at least in part on two or more of the body point locations, a first angle of a body part of the body;
and
determine that the first angle of the body part is not within a defined range;
present, through at least one output of the portable device, a request that the body part be repositioned;
subsequent to presentation of the request:
process one or more second 2D body images to determine second body point locations for each of the plurality of body points of the body;
determine, based at least in part on two or more of the second body point locations, a second angle of the body part;
determine that the second angle of the body part is within the defined range;
and
based at least in part on a determination that the second angle is within the defined range, determine that the body is positioned in a defined pose;
in response to determination that the body is positioned in the defined pose;
select a first 2D body image generated by the imaging element as a first 2D body direction image corresponding to a first direction of the body;
send, to the remote computing resource, at least the first 2D body direction image;
receive, from the remote computing resource, the 3D body model parameters corresponding to the body represented in at least the first 2D body direction image;
and
present, on a display of the portable device and based at least in part on the 3D body model parameters, a 3D body model representative of the body.

21 more elements

A method comprising:

determining that a device having an imaging element is in a first position;
processing at least a first two-dimensional (“2D”) body image received from the imaging element to at least:
determine body point locations for each of a plurality of body points of a body represented in the first 2D body image;
determine, based at least in part on two or more of the body point locations, a first angle of a body part of the body;
and
determine that the first angle of the body part is not within a defined range;
presenting, through at least one output of the device, a request that the body part be repositioned;
subsequent to presenting the request:
processing at least a second 2D body image to determine second body point locations for each of the plurality of body points of the body;
determining, based at least in part on two or more of the second body point locations, a second angle of the body part;
determining that the second angle of the body part is within the defined range;
and
based at least in part on determining that the second angle of the body part is within the defined range, determining that the body is positioned in a defined pose;
in response to determining that the body is positioned in the defined pose:
determining a first direction of the body with respect to the imaging element;
and
selecting at least one of the second 2D body image or a third 2D body image received from the imaging element as a first 2D body direction image corresponding to the body in the first direction;
sending to a remote computing resource at least the first 2D body direction image;
receiving, from the remote computing resource, 3D body model parameters representative of the body, wherein the 3D body model parameters are determined by the remote computing resource based at least in part on the first 2D body direction image;
rendering, based at least in part on the 3D body model parameters, a 3D body model representative of the body;
and
presenting, on a display of the device, the 3D body model.

19 more elements

Dependencies are inferred from the claim text.