Higher-order potentials for video object segmentation in bilateral space
Higher-order potentials for video object segmentation in bilateral space
复制标题
双边空间中视频对象分割的高阶势
DOI：
10.1016/j.neucom.2020.03.020
复制
发表时间：
2020-08-11
期刊：
影响因子：
6
通讯作者：
Wu, Enhua
中科院分区：
文献类型：
--
作者：
Hao, Chuanyan;Chen, Yadang;Wu, Enhua
我们提出了一种有效的方法来分割视频中的对象，初始输入的是源视频中的几帧对象掩码。在该方法中，我们将分割任务归结为马尔可夫随机场(MRF)标记问题。与传统的马尔可夫随机场模型不同，我们的模型使用了一个附加的高阶势项来更好地传播帧之间的全局一致性。本文提出的高阶势对该方法具有重要意义，因为它能够在分割过程中保持长范围的一致性。为了使磁流变能量最小，我们还引入了一种巧妙的技巧，在优化过程中使难以处理的高阶势“看不见”，从而可以简单地应用标准的图割算法来解决问题。此外，整个过程是在双边空间中进行的，在双边空间中可以有效地对从双边网格中定期采样的顶点进行标注。实验结果表明，该方法在多个基准数据集上的性能优于目前最先进的算法，并且具有更快的运行时间。(C)2020年由爱思唯尔出版。
We propose an effective approach to make segmentation for objects in videos with an initial input of the object masks in a few frames of the source video. In this method, we cast the segmentation task as a Markov Random Field (MRF) labeling problem. Different from the conventional MRF models, our model uses an additional term of higher-order potential to better propagate the global consistency among frames. The higher-order potential presented in this paper is significant for the proposed method because of its capability to keep the long-range consistency during segmentation. In order to make the MRF energy minimized, we also introduce a smart skill that makes the intractable higher-order potential "invisible" during the optimization so that the problem can be solved simply by applying a standard graph cut algorithm. Besides, the entire process is operated in a bilateral space, where the labeling can be inferred efficiently on the vertices that are sampled regularly from the bilateral grid. The results of a comparison of our method with a number of recently developed methods show that it performs favorably against state-of-the-art algorithms on multiple benchmark data sets in view of accuracy and achieves a much faster runtime performance. (C) 2020 Published by Elsevier B.V.