动态背景体育运动视频合成对比*

针对在同一场景下获取的体育运动视频，提出了一种基于全局运动补偿及运动前景区域信息的体育运动视频合成方法。首先，对待合成视频，通过全局运动估计与补偿，将相邻帧在空间上对齐到当前帧。通过计算帧差，得到当前帧中的运动前景区域信息。然后根据两段待合成视频之间背景的相似性，计算并修正全局运动参数，确定待合成对应帧之间的位置关系。最后，依据已经获得的运动前景区域信息，生成合成帧。实验结果表明，该方法可自动合成在同一场景中获得的有相似动态背景的体育视频，保持了前景与背景的清晰度，能清晰地显示运动员动作的差异。

Composition and Comparison of Sports Video with Dynamic Scene

An automatic composition algorithm for sports video in same scene is proposed. First, the information of the foreground areas in current frame is obtained with global motion estimation and image registration between current frame and temporally adjacent frames, Then ,the spatial relationship between the two pre-composition frames is obtained by using global motion estimation method. Finally, the composition frame is constructed based on the information of the foreground areas of both pre-composition frames. Experiments demonstrate that proposed method is robust to the dynamic scene and able to compose the sports video keeping both of the foreground areas of pre-composition frames clear.