標題: Spatially and Temporally Optimized Video Stabilization
作者: Wang, Yu-Shuen
Liu, Feng
Hsu, Pu-Sheng
Lee, Tong-Yee
資訊工程學系
Department of Computer Science
關鍵字: Video stabilization;warping;optimization;Bezier curve
公開日期: 1-Aug-2013
摘要: Properly handling parallax is important for video stabilization. Existing methods that achieve the aim require either 3D reconstruction or long feature trajectories to enforce the subspace or epipolar geometry constraints. In this paper, we present a robust and efficient technique that works on general videos. It achieves high-quality camera motion on videos where 3D reconstruction is difficult or long feature trajectories are not available. We represent each trajectory as a Bezier curve and maintain the spatial relations between trajectories by preserving the original offsets of neighboring curves. Our technique formulates stabilization as a spatial-temporal optimization problem that finds smooth feature trajectories and avoids visual distortion. The Bezier representation enables strong smoothness of each feature trajectory and reduces the number of variables in the optimization problem. We also stabilize videos in a streaming fashion to achieve scalability. The experiments show that our technique achieves high-quality camera motion on a variety of challenging videos that are difficult for existing methods.
URI: http://dx.doi.org/10.1109/TVCG.2013.11
http://hdl.handle.net/11536/22168
ISSN: 1077-2626
DOI: 10.1109/TVCG.2013.11
期刊: IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
Volume: 19
Issue: 8
起始頁: 1354
結束頁: 1361
Appears in Collections:Articles


Files in This Item:

  1. 000320658600010.pdf