Video processing method and apparatus based on multiple texture images

摘要

Disclosed herein is a video processing apparatus and method based on multiple texture images, which can process videos with optimal video quality at a low transfer rate. For this, an input video is divided into shot segments, and one is selected from a plurality of frames of each shot segment as a seed image. A plurality of texture points are detected from the seed image. The plurality of texture points are tracked from the plurality of frames of the shot segment and then spatio-temporal location transform variables for the respective texture points are calculated. A plurality of texture images are defined using texture points at which the spatio-temporal location transform variables correspond to one another.

主权项

1. A video processing method based on multiple texture images, comprising:
dividing an input video into shot segments, and selecting one from a plurality of frames of each shot segment as a seed image; detecting a plurality of texture points from the seed image; tracking the plurality of texture points from the plurality of frames of the shot segment and then calculating spatio-temporal location transform variables for the respective texture points; defining a plurality of texture images using texture points at which the spatio-temporal location transform variables correspond to one another; and merging texture images, which have spatio-temporal location transform variables for which similarities calculated by obtaining correlation characteristics between texture image signals have values falling within a preset threshold value, among the plurality of texture images, into a single texture image, thus approximating the texture images.