中文摘要：

我们开发一个新基于录像的运动分析算法决定二个人是否在他们的会议有任何相互作用。在二个人之间的相互作用能是很一般的，例如握手，等等交换目标。使运动分析柔韧到图象噪音，我们分割每个录像框架进一套 superpixels 然后由在 superpixel 以内平均光流动为每 superpixel 导出一个运动特征和一个运动模式。明确地，我们空间地并且时间地使用格子切割构造 superpixels，它是越过框架一致。基于运动特征和 superpixels 的运动模式，我们开发一个算法把一个输入录像序列划分成三个连续时期：1 ) 向对方走的二个人， 2 ) 二个人相遇对方，并且 3 ) 二个人从对方走开。建议算法能精确地区分的实验表演有或没有人的相互作用的录像。

英文摘要：

We develop a new video-based motion analysis algorithn to determine whether two persons have any interaction in their meet- ing. The interaction between two persons can be very general, such as shaking hands, exchanging objects, and so on. To make the motio~ analysis robust to image noise, we segment each video flame into a set of superpixels and then derive a motion feature and a motion pattern for each superpixel by averaging the optical flow within the superpixe Specifically, we use the lattice cut to construct the superpixels, which are spatially and temporally consistent across frames. Based on the motion feature and the motion pattern of the superpixels, we develop an algorithm to divide an input video sequence into three consecutive periods： 1） two persons walking toward each other, 2） two persons meeting each other, and 3） two persons walking away fi＇om each other. The experiment show that the proposed algorithm can accurately dis- tinguish the videos with and without human interactions.