采用统计推断的自动视频对象分割

在新一代MPEG－4视频编码标准中，为了支持面向对象编码和实现基于内容的应用，视频对象（VO）的自动分割成为关键技术之一，减背景法是视频对象自动分割的基本方法，但是不同的环境光照条件常常给视频对象的分割带来困难，提出一种基于统计推断的减背景法。该方法首先建立背景统计模型，然后对后续帧进行假设检验，从而分割出视频对象。文中算法采用HSV颜色空间，通过对背景统计模型中各颜色分量的有效分析和区别使用，能够很好地适应不同的环境光照条件。实验表明，文中算法能够在各种光照环境下自动地实现视频对象的准确分割。

Statistical Inference for Automatic Video Object Segmentation

In the new MPEG-4 video coding standard, the automatic video object segmentation plays a key role in supporting object-oriented coding and enabling content-based functionalities. Background subtraction is one of the basic methods of automatic video object segmentation. But the great variety of environmental illumination conditions often makes it hard to work. A statistical inference based background subtraction method is presented. A statistical background model is first setup, then the hypothesis testing is applied to the following frames to segment the video objects. HSV color model is also used and its color components are analyzed and treated separately so that the proposed algorithm can adapt to different environmental illumination conditions. Experimental results show this algorithm can automatically segment video objects accurately in various illuminating environments.