Motion Trajectory Segmentation via Minimum Cost Multicuts
Motion Trajectory Segmentation via Minimum Cost Multicuts
复制标题
DOI：
10.1109/iccv.2015.374
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
M. Keuper;Bjoern Andres;T. Brox
中科院分区：
文献类型：
--
作者：
M. Keuper;Bjoern Andres;T. Brox
对于视频中运动对象的分割，长期点轨迹的分析一直是非常流行的。在本文中，我们制定的视频序列的分割点轨迹的基础上，作为一个最小成本的多割问题。与常用的谱聚类公式不同，最小成本的multicut公式不仅可以优化聚类分配，还可以优化聚类的数量，同时允许不同的聚类大小。在此设置中，我们提供了一种方法来创建具有吸引力和排斥力的二进制项的长期点轨迹图，并优于基于FBMS-59数据集和VSB 100数据集的运动子任务的谱聚类的最先进方法。
For the segmentation of moving objects in videos, the analysis of long-term point trajectories has been very popular recently. In this paper, we formulate the segmentation of a video sequence based on point trajectories as a minimum cost multicut problem. Unlike the commonly used spectral clustering formulation, the minimum cost multicut formulation gives natural rise to optimize not only for a cluster assignment but also for the number of clusters while allowing for varying cluster sizes. In this setup, we provide a method to create a long-term point trajectory graph with attractive and repulsive binary terms and outperform state-of-the-art methods based on spectral clustering on the FBMS-59 dataset and on the motion subtask of the VSB100 dataset.