Our method can not only obtain the accurate contour of the video object but also make the segmentation and tracking for multiple objects. 该方法不仅能够消除差分图像中的显露背景,得到运动视频对象精确的轮廓,并且可进行多目标的分割与跟踪。
But because the video object segmentation is a difficult problem with challenge at present, MPEG organization has not made how to cut the existing digital video sequences into video object, but regard it as the open part of the standard and wait for further investigation. 然而由于视频对象分割是目前一个具有挑战性的难题,MPEG组织并没有制定如何将现有的数字视频序列分割成视频对象,而是将其作为标准的开放部分留待深入研究。
The study of video object segmentation and tracking gains some evolvements, but now it still has no a automated segmentation and tracking algorithm for all video images. 虽然,视频对象分割与跟踪的研究取得了一些进展,但目前尚没有一种通用性的全自动分割与跟踪算法。
According to the characteristics of video object shape, a new method for video object shape coding is presented which belongs to bitmap based methods, but has good scalability and coding efficiency. 根据视频对象形状的特点,提出了一种新的视频对象形状编码方法.这种方法仍然属于基于位图的方法,但是具有很好的可扩展性和压缩效率。
Dynamic textures, which are the sequences of video images, not only contain the static information derived from the structure of object, but also contain the rich motion information of object. 作为动态纹理的视频图像序列中不仅包含有物体结构方面的静态信息,而且还包含有丰富的物体运动的动态信息。