摘要
提出一种在双目视觉的条件下,利用光流金字塔跟踪算法跟踪关节点,以解决传统光流不能进行大幅度运动跟踪的问题,并利用极线约束进行三维重建获得深度信息,结合对消失关节点的位置预测求出相应的三维坐标,再利用层次化的描述方法将三维坐标转化为三维模型中各个关节点的旋转角度,实现对人体运动的模型描述。实验结果表明,该算法能有效地对人体的运动进行描述。
This paper proposed an approach that in a binocular camera system, to track key points using optical flow pyramid to solve the problem that the traditional optical flow can not solve, and reconstructing the human body to get the depth information by means of epipolar restriction, attached with the prediction of the disappear joints to get the corresponding 3D coordinates, then turned the 3D coordinates to the rotation angles with the means of hierarchical description. Experimental results show the algorithm can track complex human motion and describe.
出处
《微型机与应用》
2011年第11期41-44,48,共5页
Microcomputer & Its Applications
基金
河北省自然科学基金(08M006)
关键词
人体三维模型
光流金字塔
极线约束
层次化描述
3D human model
optical flow pyramid
epipolar restriction
hierarchical description
