Lee, Ken-YiKen-YiLeeChuang, Yung-YuYung-YuChuangChen, Bing-YuBing-YuChenYUNG-YU CHUANG2012-11-032018-07-052012-11-032018-07-05200915505499http://ntur.lib.ntu.edu.tw//handle/246246/244491https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102307210&doi=10.1109%2fICCV.2009.5459297&partnerID=40&md5=86389aac735ae63c5a62feaea11bdce9This paper proposes a new approach for video stabilization. Most existing video stabilization methods adopt a framework of three steps, motion estimation, motion compensation and image composition. Camera motion is often estimated based on pairwise registration between frames. Thus, these methods often assume static scenes or distant backgrounds. Furthermore, for scenes with moving objects, robust methods are required for finding the dominant motion. Such assumptions and judgements could lead to errors in motion parameters. Errors are compounded by motion compensation which smoothes motion parameters. This paper proposes a method to directly stabilize a video without explicitly estimating camera motion, thus assuming neither motion models nor dominant motion. The method first extracts robust feature trajectories from the input video. Optimization is then performed to find a set of transformations to smooth out these trajectories and stabilize the video. In addition, the optimization also considers quality of the stabilized video and selects a video with not only smooth camera motion but also less unfilled area after stabilization. Experiments show that our method can deal with complicated videos containing near, large and multiple moving objects. © 2009 IEEEen-USCameras; Computer vision; Motion compensation; Motion estimation; Stabilization; Camera motions; Image composition; Motion parameters; Moving objects; New approaches; Optimisations; Robust methods; Stabilization methods; Step motions; Video stabilization; Trajectoriesconference paper10.1109/ICCV.2009.54592972-s2.0-85102307210http://ntur.lib.ntu.edu.tw/bitstream/246246/244491/-1/09.pdf