基于视差和阈值分割的立体视频对象提取

视频对象分割和提取是编码、通信以及视频检索等基于内容视频处理中的关键问题，为了从只有单一全局运动、含有重叠多对象的立体视频序列中提取对象，提出了一种基于视差分析和阈值分割的对象提取方法。该方法首先用改进的区域匹配法进行立体视差估计，并通过合理减少匹配窗的运算量及根据视差特性设定搜索路径来加快匹配速度；然后针对图像中不同的对象分别采用迭代阈值法和自适应阈值法进行二次分割；最后从阈值分割结果中提取出各个对象。实验提取出的各深度层视频对象效果良好，表明该方法是一种有效的适用于全局运动的立体视频序列对象提取方法。

Stereoscopic Video Object Extraction Based on Disparity and Threshold

Object segmentation and extraction are vital tasks in many issues of content-based video processing. A video object segmentation algorithm is proposed in this paper based on disparity analysis and threshold segmentation for stereoscopic sequences including overlapped multi-objects with global motion. An improved area-based method is firstly adopted for disparity estimation by accelerating the matching processing. Then, to segment different objects in the scene, iterative threshold segmentation and self-adaptive threshold segmentation are respectively performed on the images, and the objects are extracted at last. Experimental results show that the proposed algorithm is an effective object extraction method suitable for stereoscopic sequences with unitary global motion.