Appearance-consistent Video Object Segmentation Based on a Multinomial Event Model
Appearance-consistent Video Object Segmentation Based on a Multinomial Event Model
复制标题
基于多项事件模型的外观一致的视频对象分割
DOI：
10.1145/3321507
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Wu Enhua
中科院分区：
文献类型：
--
作者：
Chen Yadang;Hao Chuanyan;Liu Alex X.;Wu Enhua
本文提出了一种在马尔可夫随机场(MRF)上实现的无约束视频对象分割算法。在MRF图中，每个节点被建模为一个超像素，并在分割过程中被标记为前景或背景。通过在几个标记帧的监督下学习导向型支持向量机分类器来计算每个节点的一元势。利用成对位势实现时空光滑性。此外，基于多项式事件模型的高阶势被用来增强整个帧的外观一致性。为了最大限度地减少这种难以处理的特性，我们还引入了一种更有效的技术，该技术简单地扩展了原始的MRF结构。该方法在不同度量的实验中进行了评估，基于基准测试的结果表明，该方法与其他最先进的算法相比是有效的。
In this study, we propose an effective and efficient algorithm for unconstrained video object segmentation, which is achieved in a Markov random field (MRF). In the MRF graph, each node is modeled as a superpixel and labeled as either foreground or background during the segmentation process. The unary potential is computed for each node by learning a transductive SVM classifier under supervision by a few labeled frames. The pairwise potential is used for the spatial-temporal smoothness. In addition, a high-order potential based on the multinomial event model is employed to enhance the appearance consistency throughout the frames. To minimize this intractable feature, we also introduce a more efficient technique that simply extends the original MRF structure. The proposed approach was evaluated in experiments with different measures and the results based on a benchmark demonstrated its effectiveness compared with other state-of-the-art algorithms.