期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 49, 期 1, 页码 159-170出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2017.2769097
关键词
Boundaries; motion; point trajectory; video
类别
资金
- National Basic Research Program of China (973 Program) [2013CB328805]
- National Natural Science Foundation of China [61272359, 61379087, 61602183]
- UGC Direct Grant for Research [4055060]
- Fok Ying Tung Education Foundation [141067]
- Specialized Fund for Joint Building Program of Beijing Municipal Education Commission
Currently, the most widely used point trajectories generation methods estimate the trajectories from the dense optical flow, by using a consistency check strategy to detect the occluded regions. However, these methods will miss some important trajectories, thus resulting in breaking smooth areas without any structure especially around the motion boundaries (MBs). We suggest exploring MBs in video to generate more accurate dense point trajectories. Estimating MBs from the video improves the point trajectory accuracy of the discontinuity or occluded areas. Then, we obtain trajectories by tracking the initial feature points through all frames. The experimental results demonstrate that our method outperforms the state-of-the-art methods on the challenging benchmark.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据