Yi Jin, Zhang Shiqiang, Cao Yueqi, Zhang Erchuan, Sun Huafei
Department of Basic Courses, Beijing Union University, Beijing 100081, China.
School of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, China.
Entropy (Basel). 2020 May 12;22(5):539. doi: 10.3390/e22050539.
Shape registration, finding the correct alignment of two sets of data, plays a significant role in computer vision such as objection recognition and image analysis. The iterative closest point (ICP) algorithm is one of well known and widely used algorithms in this area. The main purpose of this paper is to incorporate ICP with the fast convergent extended Hamiltonian learning (EHL), so called , to perform planar and spatial rigid shape registration. By treating the registration error as the potential for the extended Hamiltonian system, the rigid shape registration is modelled as an optimization problem on the special Euclidean group S E ( n ) ( n = 2 , 3 ) . Our method is robust to initial values and parameters. Compared with some state-of-art methods, our approach shows better efficiency and accuracy by simulation experiments.
形状配准，即找到两组数据的正确对齐方式，在诸如目标识别和图像分析等计算机视觉领域中发挥着重要作用。迭代最近点（ICP）算法是该领域中著名且广泛使用的算法之一。本文的主要目的是将ICP与快速收敛的扩展哈密顿学习（EHL）相结合，即所谓的 ，以执行平面和空间刚体形状配准。通过将配准误差视为扩展哈密顿系统的势能，刚体形状配准被建模为特殊欧几里得群SE(n)（n = 2, 3）上的优化问题。我们的方法对初始值和参数具有鲁棒性。通过仿真实验表明，与一些现有方法相比，我们的方法具有更高的效率和准确性。
