基于时空分析的视频前景提取

为了从包含动态背景或者非平移运动前景的视频中提取完整的前景区域，提出一种视频分割算法。首先，将视频中单个像素的变化过程视为离散时间信号，运用时间轴的Gabor滤波对时域信息进行分析，将视频粗分为前景和背景;然后，运用均值漂移算法对前景和背景做颜色聚类分析，分析空域的颜色关联信息，分别建立全局颜色模型和局部颜色模型;最后，运用双重标记法提取视频前景。该算法综合考虑视频的时域信息和空域信息。在多个视频库的测试结果表明，该算法可以显著提高前景区域提取的精度，特别是对于背景动态变化或者前景发生非平移运动的视频。

Video Foreground Segmentation Based on Analysis of Spatial-Temporal Information

An algorithm is proposed to segment foreground accurately from videos whose background is dynamic or whose foreground performs non-translational motion. Firstly, by regarding the change process of a single pixel as discrete-time signal, the video is segmented into foreground and background in a glancing way with temporal analysis using Gabor filter. Secondly, global color model and local color model are defined and built by clustering the color information of the background and foreground with mean-shift algorithm. Finally, a double-labeling method is used for fine segmentation of the foreground. Experimental results on several datasets prove that the proposed algorithm evidently improves the precision of the extracted foreground, especially in the cases that the background is dynamic or the foreground performs non-translational motion.