Technologies for automated screen segmentation
AssigneeIntel Corporation
InventorAnthony Rhodes
Life of this patent
Estimating the term…
Abstract
Examples described herein relate to automatic identification and transformation of a color region. A user can identify a region of a video frame or image that corresponds to a color region that is to be segmented. A color region can include one or more colors that appear to be approximately a uniform color. For one or more video frames, gamma correction can be applied to frames of the video. One or more frames of a video can be mapped to two color spaces. For each pixel in an image, a determination is made if the pixel has the same color as that of the identified region based on each of the at least two color spaces identifying the pixel as the color. The color region can be identified throughout a video and transformed to another color to aid in video editing.
Claims24
A computing apparatus comprising:
- a memory and
- at least one processor coupled to the memory, the at least one processor configured to:
- receive an identification of a background region of an image, wherein the image comprises the background region and at least one foreground region;
- generate at least two color space representations of at least a portion of the background region of the image;
- identify occurrences of a color associated with the background region in each of the at least two color space representations;
- and
- for a pixel in the image, based on occurrences of the color associated with the background region in each of the at least two color space representations, associate the pixel with the color associated with the background region, wherein the color associated with the background region comprises a uniform color that is independent of a foreground region of the at least one foreground region.
A non-transitory computer-readable medium comprising instructions stored thereon, that if executed by at least one processor, causes the at least one processor to:
- cause display of a user interface comprising:
- an opportunity to select a video file, an opportunity to select a frame of the selected video file, and an opportunity to select at least one background region of the frame, wherein the frame comprises the at least one background region and at least one foreground region;
- receive an indication of a selected at least one background region of a selected frame;
- generate at least two color space representations of at least a portion of the selected at least one background region;
- identify occurrences of a color associated with the selected at least one background region in each of the at least two color space representations;
- and
- for a pixel in the selected frame, based on occurrences of the color associated with the selected at least one background region in each of the at least two color space representations, associate the pixel with the color associated with the selected at least one background region, wherein the color associated with the selected at least one background region comprises a uniform color that is independent of a foreground region of the at least one foreground region.
A method comprising:
- receiving an indication of a selected background region of a frame of a video, wherein the frame comprises at least one background region and at least one foreground region;
- identifying occurrences of a color associated with the selected background region in each of at least two color space representations, wherein the color comprises a uniform color that is independent of a foreground region of the at least one foreground region;
- for a pixel in the selected background region, based on occurrences of the color associated with the selected background region in each of the at least two color space representations, associating the pixel with the color;
- transforming pixels in at least one frame of the video and associated with the color to a first color;
- transforming pixels in the at least one frame of the video and not associated with the color to a second color;
- and
- generating a modified version of the video based on the transformed pixels.
Dependencies are inferred from the claim text.