Border detection in videos
AssigneeGoogle Inc.
InventorsChen Wu, Sang-Uok Kum, Thierry Foucu
Life of this patent
Estimating the term…
Abstract
Systems and methods for border detection on videos are disclosed herein. The system can include a refinement component that updates a variable as a function of a change in line number, wherein the change in line number is ascertained in response to a change in luminance values and/or chroma values associated with a border and a video area included in a frame associated with an original video. Further, the system also includes a trimming component that, as a function of the variable, crops the border from the frame that includes the video area of the resized original video.
Claims9
A system, comprising:
- at least one non-transitory computer readable medium having stored thereon computer-executable instructions;
- at least one microprocessor that executes the computer executable instructions to perform operations comprising:
- determining a variable based on a first line number ascertained as a function of a change in luminance or chroma between a border and a video area included in a first frame of a video;
- updating the variable based on a second line number being different from the first line number, the second line number ascertained as a function of a change in luminance or chroma between the border and the video area included in a second frame of the video, the second frame subsequent to the first frame;
- and
- removing the border from each of the first frame and the second frame based on the updated variable.
A method, comprising:
- determining, by a computer system, a variable based on a first line number ascertained as a function of a change in luminance between a border area and a video area included in a first frame of a video;
- updating, by the computer system, the variable based on a second line number being different from the first line number, the second line number ascertained as a function of a change in luminance between the border area and the video area included in a second frame of the video;
- and
- removing the border area from each of the first frame and the second frame based on the updated variable.
Dependencies are inferred from the claim text.