基于H.264压缩域的镜头运动信息提取

Global Motion Estimation Method for H.264 Video

本文根据H.264编码特点,提出了一种从H.264压缩域中快速有效地进行镜头运动参数估计的算法。镜头运动信息在视频分析处理中起着重要的作用。该算法充分利用了H.264压缩码流中的信息,通过提取预测残差DC图像的运动背景区域,估计镜头运动参数,从而保证了参数估计的准确性,有效地克服了已有文献中仅仅采用运动矢量进行镜头运动估计的局限性。根据不同的H.264测试序列的对比分析,结果表明本算法可快速准确地对H.264视频序列进行全局运动信息估计,同时具有很高的鲁棒性。

In this paper, an effective global motion estimation algorithm based on the moving background derived from H.264 compressed data is presented. In order to process video data effectively, the camera motion extraction from compressed video is often required. The algorithm uses the predictive error DC-image to extract the moving background of the current frame , and then exploits a new global mo- tion estimation method based on a 6-parameters motion model to calculate the camera parameters. The experimental results show our algorithm can estimate global motion parameters more effectively and exhibit more robustness than the existing algorithm.