中文摘要：

在双视点立体系统中,运动物体跟踪是计算机视觉中一个热门的研究领域.为了精确地获得运动物体的像素点,我们提出了一个新的物体跟踪算法：首先计算运动物体的特征点,然后对其进行匹配,最后连接匹配的特征点并形成轨迹.算法在分辨率为640×480和768×576的视频文件中进行.结果表明：与L-K光流法相比,新算法可以更鲁棒性地检测运动物体并获得更精确的运动轨迹.

英文摘要：

Tracking moving object in dual-view stereo system is becoming a hot research area in computer vision. To capture the moving objects pixels more accurately, a new object tracking algorithm is proposed to first compute moving objects feature points and then match these points, finally connect the matching feature points and get objects motion trajectories. The algorithm is tested in the video sequences with resolution 640）〈 480 and 768）〈 576 individually. The results show that the algorithm is more robust and the trajectories of the moving objects tracked with our method are more accurate compared with current method of L--K optical flow.