Image segmentation for object modeling
AssigneeSnap Inc.
InventorMaksim Igorevich Gusarov
Life of this patent
Estimating the term…
Abstract
Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by accessing a set of images within a video stream, identifying an object of interest within one or more images of the set of images, and detecting a region of interest within the one or more images. The systems, devices, and method identify a first set of median pixels in a first portion of the object of interest and a second set of median pixels in a second portion of the object of interest. The systems, devices, and methods determine a polyline approximating the first and second sets of median pixels and generate a model for the polyline.
Claims19
A computer implemented method comprising:
- identifying, by a processor, an object in an image;
- detecting, by the processor, a perimeter of the identified object;
- identifying, by the processor, extremity points of the perimeter;
- using the identified extremity points of the perimeter, generating, by the processor, a region for encompassing the object, having a size that is a function of a distance between the extremity points and a predetermined value;
- determining a bend position between a first portion of the object and a second portion of the object;
- determining a first line extending in a first direction from the bend position, the first line extending across one or more of a first set of median pixels of the first portion;
- and
- determining a second line extending in a second direction from the bend position, the second line extending across one or more of a second set of median pixels of the second portion;
- and
- generating, by the processor, a model of the object based on the generated region encompassing the object, and the first and second lines.
A system, comprising:
- one or more processors;
- and
- a non-transitory processor-readable storage medium storing processor executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- identifying an object in an image;
- detecting a perimeter of the identified object;
- identifying extremity points of the perimeter;
- using the identified extremity points of the perimeter, generating a region for encompassing the object, having a size that is a function of a distance between the extremity points and a predetermined value;
- and
- determining a bend position between a first portion of the object and a second portion of the object;
- determining a first line extending in a first direction from the bend position, the first line extending across one or more of a first set of median pixels of the first portion;
- and
- determining a second line extending in a second direction from the bend position, the second line extending across one or more of a second set of median pixels of the second portion;
- and
- generating a model of the object based on the generated region encompassing the object, and the first and second lines.
A non-transitory processor-readable storage medium storing processor executable instructions that, when executed by a processor of a machine, cause the machine to perform operations comprising:
- identifying an object in an image;
- detecting a perimeter of the identified object;
- identifying extremity points of the perimeter;
- using the identified extremity points of the perimeter, generating a region for encompassing the object, having a size that is a function of a distance between the extremity points and a predetermined value;
- and
- determining a bend position between a first portion of the object and a second portion of the object;
- determining a first line extending in a first direction from the bend position, the first line extending across one or more of a first set of median pixels of the first portion;
- and
- determining a second line extending in a second direction from the bend position, the second line extending across one or more of a second set of median pixels of the second portion;
- and
- generating a model of the object based on the generated region encompassing the object, and the first and second lines.
Dependencies are inferred from the claim text.