Body modeling using mobile device
Methods, systems and computer readable media for computerized modeling of a subject (e.g., a human body) are described.
1. A method comprising:
receiving, at one or more processors, a video that includes a plurality of image frames in a sequence as input;
separating, using the one or more processors, the video into a plurality of individual image frames;
selecting a group of one or more image frames from the plurality of individual image frames;
for each individual image frame in the group of one or more image frames, performing operations including:
identifying human body regions corresponding to a human body subject within the image frame;
segmenting the image frame to remove image features that are not parts of the human body subject;
aligning the human body subject within the image frame, wherein the aligning includes adjusting for vertical or horizontal movement of the human body subject from one frame to another and centering the human body subject image within the frame;
generating a silhouette of the human body subject within the image frame; and
determining one or more orientations of the human body subject based on the image frame;
determining a location of a waistline of the human body subject in the image frame based on the one or more orientations;
projecting an ellipse from the human body subject based on a rotation of the silhouette of the human body subject;
fitting an ellipse equation to the projected ellipse;
determining an estimated waistline perimeter for the human body subject based on the ellipse equation;
receiving one or more demographic information items corresponding to the human body subject;
retrieving an estimated demographic waistline perimeter from a data store based on the one or more demographic information items; and
generating an adjusted estimated waistline perimeter by adjusting the estimated waistline perimeter based on the estimated demographic waistline perimeter.
2. The method of claim 1 , wherein projecting the ellipse includes projecting one or more individual waist diameters onto a plane about an origin such that the one or more individual waist diameters can be fit to an ellipse using least-squares to determine an ellipse approximating waistline perimeter.
3. The method of claim 1 , wherein determining one or more orientations of the human body subject is based on an area of the human body subject in a first image frame and a second image frame.
4. The method of claim 1 , wherein aligning includes adjusting for vertical or horizontal movement of the human body subject image between a plurality of frames of the video and centering the human body subject image within the frame.
5. The method of claim 1 , wherein the adjusting includes determining a mathematical mean of the estimated waistline perimeter and the estimated demographic waistline perimeter.
6. The method of claim 1 , wherein determining a location of a waistline of the human body subject is based a measurement of the human body subject.
7. The method of claim 6 , wherein the measurement includes height of the human body subject.
8. The method of claim 7 , wherein the measurement is received via a graphical user interface.
9. The method of claim 1 , further comprising deleting the video and the plurality of individual image frames and retaining the estimated waistline perimeter or adjusted estimated waistline perimeter.
10. A system comprising:
a memory; and
a processing device, coupled to the memory, the processing device configured to perform operations including:
receiving, at one or more processors, a video that includes a plurality of image frames in a sequence as input;
separating, using the one or more processors, the video into a plurality of individual image frames;
selecting a group of one or more image frames from the plurality of individual image frames;
for each individual image frame in the group of one or more image frames, performing operations including:
identifying human body regions corresponding to a human body subject within the image frame;
segmenting the image frame to remove image features that are not parts of the human body subject;
aligning the human body subject within the image frame, wherein the aligning includes adjusting for vertical or horizontal movement of the human body subject from one frame to another and centering the human body subject image within the frame;
generating a silhouette of the human body subject within the image frame; and
determining one or more orientations of the human body subject based on the image frame;
determining a location of a waistline of the human body subject in the image frame based on the one or more orientations;
projecting an ellipse from the human body subject based on a rotation of the silhouette of the human body subject;
fitting an ellipse equation to the projected ellipse; and
determining an estimated waistline perimeter for the human body subject based on the ellipse equation,
wherein projecting the ellipse includes projecting one or more individual waist diameters onto a plane about an origin such that the one or more individual waist diameters can be fit to an ellipse using least-squares to determine an ellipse approximating waistline perimeter.
11. The system of claim 10 , wherein aligning includes adjusting for vertical or horizontal movement of the human body subject image between a plurality of frames of the video and centering the human body subject image within the frame.
12. The system of claim 10 , wherein the operations further include:
receiving one or more demographic information items corresponding to the human body subject;
retrieving an estimated demographic waistline perimeter from a data store based on the one or more demographic information items; and
generating an adjusted estimated waistline perimeter by adjusting the estimated waistline perimeter based on the estimated demographic waistline perimeter.
13. The system of claim 12 , wherein the operations further include deleting the video and the plurality of individual image frames and retaining the estimated waistline perimeter or adjusted estimated waistline perimeter.
14. A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, cause the processing device to perform operations comprising:
receiving, at one or more processors, a video that includes a plurality of image frames in a sequence as input;
separating, using the one or more processors, the video into a plurality of individual image frames;
selecting a group of one or more image frames from the plurality of individual image frames;
for each individual image frame in the group of one or more image frames, performing operations including:
identifying human body regions corresponding to a human body subject within the image frame;
segmenting the image frame to remove image features that are not parts of the human body subject;
aligning the human body subject within the image frame, wherein the aligning includes adjusting for vertical or horizontal movement of the human body subject from one frame to another and centering the human body subject image within the frame;
generating a silhouette of the human body subject within the image frame; and
determining one or more orientations of the human body subject based on the image frame;
determining a location of a waistline of the human body subject in the image frame based on the one or more orientations;
projecting an ellipse from the human body subject based on a rotation of the silhouette of the human body subject;
fitting an ellipse equation to the projected ellipse; and
determining an estimated waistline perimeter for the human body subject based on the ellipse equation,
wherein projecting the ellipse includes projecting one or more individual waist diameters onto a plane about an origin such that the one or more individual waist diameters can be fit to an ellipse using least-squares to determine an ellipse approximating waistline perimeter.
15. The non-transitory computer-readable medium of claim 14 , wherein aligning includes adjusting for vertical or horizontal movement of the human body subject image between a plurality of frames of the video and centering the human body subject image within the frame.
16. The non-transitory computer-readable medium of claim 14 , wherein the operations further include:
receiving one or more demographic information items corresponding to the human body subject;
retrieving an estimated demographic waistline perimeter from a data store based on the one or more demographic information items; and
generating an adjusted estimated waistline perimeter by adjusting the estimated waistline perimeter based on the estimated demographic waistline perimeter.
17. The non-transitory computer-readable medium of claim 16 , wherein the operations further include deleting the video and the plurality of individual image frames and retaining the estimated waistline perimeter or adjusted estimated waistline perimeter.