Feature-Based Video Compression

Abstract

Systems and methods of processing video data are provided. Video data having a series of video frames is received and processed. One or more instances of a candidate feature are detected in the video frames. The previously decoded video frames are processed to identify potential matches of the candidate feature. When a substantial amount of portions of previously decoded video frames include instances of the candidate feature, the instances of the candidate feature are aggregated into a set. The candidate feature set is used to create a feature-based model. The feature-based model includes a model of deformation variation and a model of appearance variation of instances of the candidate feature. The feature-based model compression efficiency is compared with the conventional video compression efficiency.

What is claimed is: 
     
         1 . A computer implemented method of processing video data formed of a series of video frames comprising:
 using a first video encoding process and a feature-based encoding process, processing the video frames by:   encoding the video frames with the first video encoding process;   processing one or more of the frames to detect one or more instances of a feature by searching the one or more frames for a region of pels having coherency and computational complexity as compared to other pels in the one or more frames;   modeling variation of the feature instance relative to other instances of the feature to create a feature-based encoding of the feature instance; and   comparing compression efficiency of the feature-based encoding of the feature instance relative to an encoding of the feature instance resulting from the first video encoding process.