Processor implemented systems and methods for handling of occlusion for frame rate upconversion

摘要

Systems and methods are provided for determining pixels in an interpolated frame. A motion vector field is determined based on movement of pixels between first and second frames. A region of the motion vector field is clustered based on similarity of motion vectors of the motion vector field within the region. A region of discontinuity is identified comprising a portion of the motion vector field not belonging to a cluster. A determination is made as to whether the region of discontinuity is an occlusion region or a reveal region. A portion of the region of discontinuity in the interpolated frame is filled using pixel data from the first frame when the region of discontinuity is an occlusion region, and a portion of the region of discontinuity in the interpolated frame is filled using pixel data from the second frame when the region of discontinuity is a reveal region.

主权项

1. A processor implementable method comprising:
receiving from a video source, (i) a first video frame consisting of first blocks of pixels, and (ii) a second video frame consisting of second block pixels, wherein the second video frame is after the first video frame in time; and generating an interpolated video frame based on pixels in the first video frame and the pixels in the second video frame, wherein generating the interpolated video frame comprises
generating a motion vector field based on movement of pixels between the first video frame and the second video frame, the motion vector field including a plurality of motion vectors that identify motion of corresponding blocks of pixels from the first video frame to the second video frame,identifying a region of discontinuity in the motion vector field, wherein motion vectors for pixels in the region of discontinuity differ significantly from motion vectors for surrounding pixels,determining whether the region of discontinuity is due to (i) the first video frame containing background objects which are not visible in the second video frame or (ii) the second video frame containing background objects which are not visible in the first video frame,in response to the region of discontinuity being due to the first video frame containing background objects which are not visible in the second video frame, selecting a pixel patch from the first video frame,in response to the region of discontinuity being due to the second video frame containing background objects which are not visible in the first video frame, selecting the pixel patch from the second video frame,selecting a location in the interpolated frame for positioning the selected pixel patch such that a portion of the pixel patch that overlaps the surrounding pixels matches the surrounding pixels, andfilling the region of discontinuity in the interpolated frame with pixels of the selected pixel patch, with the patch positioned in the selected location, wherein the selected pixel patch is of sufficient size to both completely cover the region of discontinuity and overlap the surrounding pixels, wherein the location for positioning the selected pixel patch is selected so that a portion of the selected pixel patch that overlaps with the surrounding pixels covers the surrounding pixels.