基于混合特征的非刚性点阵配准算法

Non-rigid Point Set Registration with Mixed Features

提出一种基于混合特征的非刚性点阵配准算法.该算法包含了对应关系评估与空间变换更新两个相互交替的步骤.首先定义了两个特征描述法用于描述两个点阵之间的全局和局部几何结构特征差异,随后合并这两个特征描述法建立一个基于混合特征的能量优化方程.该能量优化方程可以利用线性分配技术进行求解,同时可以灵活地选择使用最小化全局结构特征差异或最小化局部结构特征差异来评估两个点阵之间的对应关系.为了增强前述两个步骤之间的协调性,我们利用能量权重调节在整个配准过程中控制能量优化从最小化局部结构特征差异逐步转变为最小化全局结构特征差异,同时控制用于空间变换的薄板样条函数(Thin plate spline)的更新从刚性变换逐步转变为非刚性变换.我们在二维轮廓配准、三维轮廓配准、序列图像配准和图像特征点配准下对本文算法进行了各项性能测试,同时也与当前8种流行算法进行了性能比较.本文算法展现了卓越的非刚性配准性能,并在大部分实验中超越了当前的相关算法.

We present a novel non-rigid point set registration method with mixed features. The proposed method is designed by an alternating two-step process： correspondence estimation and transformation updating. We first design a global and a local feature descriptors for assessing the global and local structural differences between two point sets, respectively. The two feature descriptors are then combined for forming a mixed feature based energy function, so as to provide a flexible way to estimate correspondences by minimizing global or locM structurM differences using a linear assignment solution. To improve the interactions between the two steps, a tradeoff of energy adjustment is used to gradually adjust the energy minimization from local to global structural differences and the thin plate spline transformation from rigid to non-rigid during registration. We evaluate the performances of our method in contour registration, sequence images and real images; through comparision with other eight state-of-the-art methods, our method shows the best alignments in most deformation and rotation scenarios.