An adaptive dictionary learning approach for modeling dynamical textures
An adaptive dictionary learning approach for modeling dynamical textures
复制标题
DOI：
10.1109/icassp.2014.6854265
复制
发表时间：
2013-12
期刊：
影响因子：
--
通讯作者：
Xian Wei;Hao Shen;M. Kleinsteuber
中科院分区：
文献类型：
--
作者：
Xian Wei;Hao Shen;M. Kleinsteuber
视频表示是计算机视觉社区中一项重要且具有挑战性的任务。在本文中，我们假设移动场景的图像帧可以建模为马尔可夫随机过程。我们提出了一种稀疏编码框架，称为自适应视频字典学习（AVDL），用于自适应地对视频进行建模。开发的框架能够通过探索连续视频帧的稀疏属性和时间相关性来捕获移动场景的动态。将所提出的方法与几个基准数据序列上最先进的视频处理方法进行比较，这些基准数据序列表现出外观变化和严重遮挡。
Video representation is an important and challenging task in the computer vision community. In this paper, we assume that image frames of a moving scene can be modeled as a Markov random process. We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively. The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames. The proposed method is compared with state of the art video processing methods on several benchmark data sequences, which exhibit appearance changes and heavy occlusions.