Robust video stabilization based on motion vectors


This paper p rop oses a new robust video stabilization algorithm to remove unwanted vibrations in video sequences . A complete theoretical analysis is first establis hed f or video stabilization , p roviding a basis f or new stabilization algorithm. Secondly , a new robust global motion estimation ( GME) algorithm is p rop osed. Different from classic methods , the GME algorithm is based on spatial2temp oral filtered motion vectors comp uted by block2matching methods . In addition , effective schemes are employed in correction p hase to p re2 vent boundary artifacts and error accumulation. Experiments s how that the p rop osed algorithm has satisfactory stabilization effects while maintaining good tradeoff between speed and p recision. Key words  video stabilization , global motion , robust estimation.

Journal of Shanghai University (English Edition)
Li Song
Li Song
Professor, IEEE Senior Member

Professor, Doctoral Supervisor, the Deputy Director of the Institute of Image Communication and Network Engineering of Shanghai Jiao Tong University, the Double-Appointed Professor of the Institute of Artificial Intelligence and the Collaborative Innovation Center of Future Media Network, the Deputy Secretary-General of the China Video User Experience Alliance and head of the standards group.