A simple division model in compressed video super resolution
Super resolution based on compressed video is combing a set of frame sequence in a compressed video to reconstruct a high resolution image.It is important to get accurate motion vectors between frames from the rough motion vectors contained in the compressed video.A simple division model is proposed to improve the accuracy of the motion vectors.It is considering the video scenes with several moving objects.The division model will divide the scene into the background area and moving objects areas.In the background area,the motion vectors are set to be consistent.Then a MAP-based compressed video super resolution algorithm is applied.The super resolution result is showed in real video experiments.
component super resolution compressed video division model local motion segment
Chen An
Automation department Tsinghua University Beijing,China
国际会议
太原
英文
340-344
2011-02-26（万方平台首次上网日期，不代表论文的发表时间）