De-interlacing and frame rate upconversion for high definition video

摘要

Technologies and implementations for de-interlacing an interlaced digital video and up-converting a frame rate of a digital video are generally disclosed.

主权项

1. A method to up-convert a video, the method comprising:
inserting, by a computing device, an interpolated video frame between a first video frame and a second video frame of the video; determining, for each pixel in the interpolated video frame, whether the pixel is a background pixel based at least in part on pixels in the first video frame and pixels in the second video frame; setting, in response to determination that the pixel in the interpolated video frame is a background pixel, a value of the pixel in the interpolated video frame based at least in part on a value of a corresponding pixel in the first video frame and a value of a corresponding pixel in the second video frame; and setting, in response to determination that the pixel in the interpolated video frame is not a background pixel, the value of the pixel in the interpolated video frame based at least in part on application of a nonlocal means filter to the first video frame and the second video frame; wherein the setting, in response to determination that the pixel in the interpolated video frame is a background pixel, the value of the pixel in the interpolated video frame based at least in part on the value of the corresponding pixel in the first video frame and the value of the corresponding pixel in the second video frame includes:
determining whether the corresponding pixel in the first video frame and the corresponding pixel in the second video frame have a substantially same value;setting, in response to determination that the corresponding pixel in the first video frame and the corresponding pixel in the second video frame have substantially the same value, the value of the pixel in the interpolated video frame to be substantially equal to either the value of the corresponding pixel in the first video frame or the value of the corresponding pixel in the second video frame; andsetting, in response to determination that the corresponding pixel in the first video frame and the corresponding pixel in the second video frame do not have substantially the same value, the value of the pixel in the interpolated video frame based at least in part on application of the nonlocal means filter to the first video frame and the second video frame.