Li Linhao, Hu Qinghua, Li Xin
IEEE Trans Image Process. 2018 Nov 22. doi: 10.1109/TIP.2018.2882926.
In conventional wisdom of video modeling, background is often treated as the primary target and foreground is derived using the technique of background subtraction. Based on the observation that foreground and background are two sides of the same coin, we propose to treat them as peer unknown variables and formulate a joint estimation problem, called Hierarchical modeling and Alternating Optimization (HMAO). The motivation behind our hierarchical extensions of background and foreground models is to better incorporate a priori knowledge about the disparity between background and foreground. For background, we decompose it into temporally low-frequency and high-frequency components for the purpose of better characterizing the class of video with dynamic background; for foreground, we construct a Markov random field prior at a spatially low resolution as the pivot to facilitate noise-resilient refinement at higher resolutions. Built on hierarchical extensions of both models, we show how to successively refine their joint estimates under a unified framework known as alternating direction multipliers method. Experimental results have shown that our approach produces more discriminative background and demonstrates better robustness to noise than other competing methods. When compared against current state-of-the-art techniques, HMAO achieves at least comparable and often superior performance in terms of F-measure scores especially for video containing dynamic and complex background.
在视频建模的传统观念中，背景通常被视为主要目标，而前景则通过背景减法技术来推导。基于前景和背景是同一事物的两个方面这一观察结果，我们建议将它们视为对等的未知变量，并提出一个联合估计问题，称为分层建模与交替优化（HMAO）。我们对背景和前景模型进行分层扩展的动机是为了更好地纳入关于背景和前景之间差异的先验知识。对于背景，我们将其分解为时间上的低频和高频分量，以便更好地刻画具有动态背景的视频类别；对于前景，我们在空间低分辨率下构建一个马尔可夫随机场先验作为核心，以促进在更高分辨率下的抗噪细化。基于这两个模型的分层扩展，我们展示了如何在称为交替方向乘子法的统一框架下连续细化它们的联合估计。实验结果表明，我们的方法产生的背景更具判别力，并且比其他竞争方法对噪声具有更好的鲁棒性。与当前的最先进技术相比，HMAO在F值分数方面至少具有可比的性能，并且在包含动态和复杂背景的视频中通常表现更优。
