VabCut: A video extension of GrabCut for unsupervised video foreground object segmentation
VabCut: A video extension of GrabCut for unsupervised video foreground object segmentation
复制标题
VabCut：GrabCut 的视频扩展，用于无监督视频前景对象分割
DOI：
10.5220/0004677103620371
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
S. Satoh
中科院分区：
文献类型：
--
作者：
Sébastien Poullot;S. Satoh
本文介绍了VabCut，GrabCut的视频扩展，一个原始的无监督解决方案，以解决视频前景对象分割任务。Vabcut将RGB色域扩展到RGBM，其中M是运动。它需要一个预先的步骤：计算帧的运动层（M层）进行分割。为了计算这一层，我们建议将要分割的帧与N个时间上接近的对齐帧相交。本文还介绍了一种新的迭代和协作的最佳帧对齐方法，基于兴趣点和RANSAC，自动丢弃离群值，并依次细化单应性。整个方法是全自动的，可以处理标准视频，即不专业，不稳定，模糊或其他。我们在SegTrack 2011基准测试中测试了VabCut，并证明了它的有效性，它在速度更快的同时优于最先进的方法。
This paper introduces VabCut, a video extension of GrabCut, an original unsupervised solution to tackle the video foreground object segmentation task. Vabcut works on an extension of the RGB colour domain to RGBM, where M is the motion. It requires a prior step: the computation of the motion layer (M-layer) of the frame to segment. In order to compute this layer we propose to intersect the frame to segment with N temporally close aligned frames. This paper also introduces a new iterative and collaborative method for an optimal frame alignment, based on points of interest and RANSAC, which automatically discards outliers and refines the homographies in turns. The whole method is fully automatic and can handle standard video, i.e. not professional, shaky, blurry or else. We tested VabCut on the SegTrack 2011 benchmark, and demonstrated its effectiveness, it especially outperforms the state of the art methods while being faster.