Application specific video format
View Patent ↗A method, system, and medium are provided for formatting video frames such that a region of interest is emphasized and the video frames can be encoded, communicated, and rendered without excessive processing burdens. A region of interest is identified in a video frame and a feature mask is created that represents the region of interest. The feature mask can be used to crop the video frame to remove background images that are not within the region of interest and the cropped video frame can be overlayed on a simulated background before being encoded and communicated to a display device.
1. One or more non-transitory computer-readable media having computer-executable instructions embodied thereon for performing a method of providing a formatted video stream that emphasizes a region of interest, the method comprising:
receiving a video stream comprising a plurality of video frames;
identifying a region of interest represented by the video stream;
creating a plurality of formatted video frames by formatting each of the plurality of video frames using a feature mask of the region of interest, each of the plurality of formatted video frames comprising the region of interest overlaid on a simulated background;
encoding the plurality of formatted video frames; and
communicating the encoded plurality of formatted video frames to a display device such that the plurality of video frames can be displayed.
2. The media of claim 1 , wherein identifying the region of interest comprises applying an edge-detection algorithm to each of the plurality of video frames.
3. The media of claim 1 , wherein creating the plurality of formatted video frames comprises:
removing a background image from each of the plurality of video frames, the background image of each of the plurality of video frames comprising an image occupying a background region of each of the plurality of video frames, wherein the background region of each of the plurality of video frames comprises the portion of each of the plurality of video frames that does not include the region of interest; and
creating a simulated background by filling the background region of each of the plurality of video frames with a simulated background image.
4. The media of claim 3 , wherein the simulated background image comprises a single color.
5. The media of claim 4 , wherein the single color is blue.
6. The media of claim 1 , wherein each of the plurality of video frames comprises an image of a person captured by a video capturing device.
7. The media of claim 6 , wherein the region of interest comprises a region of each image comprising at least one of the person's hands and the person's face.
8. The media of claim 1 , further comprising formatting the region of interest such that the region of interest can be displayed in black and white.
9. The media of claim 1 , wherein encoding the plurality of formatted video frames comprises utilizing a standard video compression algorithm.
10. The media of claim 9 , wherein the standard video compression algorithm generates a compressed video stream according to an MPEG format.
11. One or more non-transitory computer-readable media having computer-executable instructions embodied thereon for performing a method of formatting a video stream to isolate features, the method comprising:
receiving a video frame;
identifying a region of interest of the video frame that corresponds to one or more features;
creating a feature mask that comprises the region of interest;
cropping the video frame using the feature mask to create a cropped video frame comprising only the region of interest; and
overlaying the cropped video frame on a simulated background to create a formatted video frame.
12. The media of claim 11 , wherein identifying the region of interest comprises applying an edge-detection algorithm to the video frame.
13. The media of claim 11 , wherein cropping the video frame comprises removing a background from the video frame, the background comprising a background image occupying a background region of the video frame, wherein the background region comprises the portion of the video frame that does not include the region of interest.
14. The media of claim 13 , wherein the simulated background comprises a simulated background image designed to occupy the background region of the video frame.
15. The media of claim 14 , wherein the simulated background image comprises a single color.
16. The media of claim 11 , further comprising formatting the cropped video frame such that the region of interest is configured to be displayed as a black and white image.
17. A system for formatting a video stream to isolate features, the system comprising:
a video driver that receives video frames from a video capturing device;
a video formatting component that:
(1) receives video frames from the video driver;
(2) identifies a region of interest of the video frames, generates a feature mask based on the identified region of interest;
(3) crops the video frames using the feature mask; and
(4) creates formatted video frames, each of the formatted video frames comprising the region of interest overlaid on a simulated background; and
a video codec for encoding the formatted video frames.
18. The system of claim 17 , wherein the video formatting component comprises an edge detection module for identifying the region of interest and generating feature mask representing the region of interest.
19. The system of claim 18 , wherein the video formatting component further comprises a cropping module for removing a background image from a video frame, wherein the background image comprises an image occupying a portion of the video frame that does not include the region of interest.
20. The system of claim 19 , wherein the video formatting component further comprises a simulated background generation module that generates a simulated background for replacing the removed background image.