Capturing Intention-based Full-Frame Video Stabilization

Abstract

Annoying shaky motion is one of the significant problems in home videos, since hand shake is an unavoidable effect when capturing by using a hand-held camcorder. Video stabilization is an important technique to solve this problem, but the stabilized videos resulting from some current methods usually have decreased resolution and are still not so stable. In this paper, we propose a robust and practical method of full-frame video stabilization while considering user s capturing intention to remove not only the high frequency shaky motions but also the low frequency unexpected movements. To guess the user s capturing intention, we first consider the regions of interest in the video to estimate which regions or objects the user wants to capture, and then use a polyline to estimate a new stable camcorder motion path while avoiding the user s interested regions or objects being cut out. Then, we fill the dynamic and static missing areas caused by frame alignment from other frames to keep the same resolution and quality as the original video. Furthermore, we smooth the discontinuous regions by using a three-dimensional Poisson-based method. After the above automatic operations, a full-frame stabilized video can be achieved and the important regions and objects can also be preserved.