基于等距随机游走图的三维动态曲面对准

Three-dimensional dynamic surface alignment based on isometric random walk graph

为了提高三维动态曲面在噪声和遮挡下的对准精度,提出时空等距随机游走图算法.该算法根据相邻两帧采样点的乘积空间定义图节点,通过时空相邻性进行节点裁剪处理.以测地距离定义图边约束,将等距映射转化为图稳定性节点选择的随机游走问题.通过马尔可夫链理论,计算得到最终的对应结果.通过对不同动态曲面数据库的实验分析表明,该算法针对具有明显噪声和空洞的三维动态曲面能够得到一致性对准关系,性能优于已有算法.

A space-time isometric random walk graph was proposed in order to improve the alignment accuracy of three-dimensional dynamic surfaces under noise and occlusion.Graph nodes were defined according to the product space of sampling point sets,and pruning was performed based on spatial-temporal adjacency.The edge weight was defined by the geodesic distance.The isometric mapping problem was formulated into the choice among a random walk graph.The alignment results were computed by Markov chain theory.The experimental results of different dynamic surface databases show that the proposed algorithm can obtain a consistent alignment for three-dimensional dynamic surface with obvious noise and holes.The aligning accuracy of the algorithm is better than the existing algorithms.