Saliency-Aware Video Object Segmentation
Saliency-Aware Video Object Segmentation
复制标题
DOI：
10.1109/tpami.2017.2662005
复制
发表时间：
2018
影响因子：
23.6
通讯作者：
Wenguan Wang;Jianbing Shen;Ruigang Yang;F. Porikli
中科院分区：
文献类型：
--
作者：
Wenguan Wang;Jianbing Shen;Ruigang Yang;F. Porikli
视频显著度旨在估计序列中的单个主导对象，为非监督视频对象分割提供强烈的对象级线索。在这篇文章中，我们提出了一种基于测地距离的技术，它提供了可靠的和时间上一致的超像素显著测量作为逐个像素标记的先验。该方法使用由时空边缘或外观和运动构造的无向帧内和帧间图，以及进一步增强显著估计的骨架提取步骤，将像素分割任务描述为一个函数的能量最小化问题，该函数由全局前景和背景模型的一元项、动态位置模型和标签光滑势的成对项组成。我们在基准数据集上进行了广泛的定量和定性实验。与目前最先进的方法相比，我们的方法在精度和速度方面取得了优越的性能。
Video saliency, aiming for estimation of a single dominant object in a sequence, offers strong object-level cues for unsupervised video object segmentation. In this paper, we present a geodesic distance based technique that provides reliable and temporally consistent saliency measurement of superpixels as a prior for pixel-wise labeling. Using undirected intra-frame and inter-frame graphs constructed from spatiotemporal edges or appearance and motion, and a skeleton abstraction step to further enhance saliency estimates, our method formulates the pixel-wise segmentation task as an energy minimization problem on a function that consists of unary terms of global foreground and background models, dynamic location models, and pairwise terms of label smoothness potentials. We perform extensive quantitative and qualitative experiments on benchmark datasets. Our method achieves superior performance in comparison to the current state-of-the-art in terms of accuracy and speed.