System and method for using feature tracking techniques for the generation of masks in the conversion of two-dimensional images to three-dimensional images
First Claim
Patent Images
1. A method of generating a mask for use in generating 2-D to 3-D conversion of an object within an image, said image being present as an image-set across multiple frames of said image, said method comprising:
- establishing, on a processor-based system, a polygon of said object within a subset of said image-set;
selecting, on the processor-based system, at least one feature of said image-set;
tracking all endpoints of vertices of said polygon for all frames of said multiple frames of said image-set;
determining if said at least one selected feature is missing from certain frames of said multiple frames of said image-set;
auto-correcting a vertex of said polygon associated with said at least one selected feature into said certain frames when said at least one selected feature is determined by the processor-based system to be missing from said certain frames; and
generating a mask of said object to fit said at least one selected feature.
2 Assignments
0 Petitions
Accused Products
Abstract
The present invention is directed to systems and methods for controlling 2-D to 3-D image conversion and/or generation. The methods and systems use auto-fitting techniques to create a mask based upon tracking features from frame to frame. When features are determined to be missing they are added prior to auto-fitting the mask.
-
Citations
19 Claims
-
1. A method of generating a mask for use in generating 2-D to 3-D conversion of an object within an image, said image being present as an image-set across multiple frames of said image, said method comprising:
-
establishing, on a processor-based system, a polygon of said object within a subset of said image-set; selecting, on the processor-based system, at least one feature of said image-set; tracking all endpoints of vertices of said polygon for all frames of said multiple frames of said image-set; determining if said at least one selected feature is missing from certain frames of said multiple frames of said image-set; auto-correcting a vertex of said polygon associated with said at least one selected feature into said certain frames when said at least one selected feature is determined by the processor-based system to be missing from said certain frames; and generating a mask of said object to fit said at least one selected feature. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system for establishing a mask for use in generating 2-D to 3-D conversion of an object within an image, said image being present as an image-set across multiple frames of said image, said system comprising:
-
a memory storing executable instructions; one or more processors operatively coupled to the memory to execute the executable instructions from the memory, the one or more processors being configured to; execute control sequences for establishing a polygon of said object within a subset of said image-set; execute control sequences for selecting at least one feature of said image-set; execute control sequences for tracking all endpoints of vertices of said polygon for all frames of said multiple frames of said image-set; execute control sequences for determining if said at least one selected feature is missing from certain frames of said multiple frames of said image-set; execute control sequences for auto-correcting a vertex of said polygon associated with said at least one selected feature into said certain frames when said at least one selected feature is determined to be missing from said certain frames; and execute control sequences for generating a mask of said object to fit said at least one selected feature. - View Dependent Claims (11, 12, 13)
-
-
14. A non-transitory, machine-readable storage medium comprising instructions stored therein, the instructions executable by one or more processors to facilitate performing a method of generating a mask for use in generating 2-D to 3-D conversion of an object within an image, said image being present as an image-set across multiple frames of said image, said method comprising:
-
establishing a polygon of said object within a subset of said image-set; selecting at least one feature of said image-set; tracking all endpoints of vertices of said polygon for all frames of said multiple frames of said image-set; determining if said at least one selected feature is missing from certain frames of said multiple frames of said image-set; auto-correcting a vertex of said polygon associated with said at least one selected feature into said certain frames when said at least one selected feature is determined to be missing from said certain frames; and generating a mask of said object to fit said at least one selected feature. - View Dependent Claims (15, 16, 17, 18, 19)
-
Specification