基于控制点一致性约束的点集仿射配准算法  

Point Set Affine Registration Algorithm Based on Control Point Consistency Constraint

作　　者：吴礼洋 凌粼 贾方超 杜少毅[2] 胡智勇 Wu Liyang;Ling Lin;Jia Fangchao;Du Shaoyi;Hu Zhiyong(Department of Ground-to-Air Navigation , Air Force Com nt unication NCO Academy, Dalian , Liaoning 116600, China;Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi' an , Shaanxi 710049, China)

机构地区：[1]空军通信士官学校地空导航系,辽宁大连116600 [2]西安交通大学人工智能与机器人研究所,陕西西安710049

出　　处：《激光与光电子学进展》2019年第9期125-131,共7页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61379104,61372167)

摘　　要：提出一种基于控制点一致性约束的稳健仿射迭代最近点算法,该方法通过建立控制点约束下的目标函数,引导数据点集仿射配准到目标点集,建立数据点集和目标点集的最近点对应关系,采用随机抽样一致性方法筛选高精度形状控制点,实现控制点约束下的目标函数更新仿射变换。实验结果表明,与传统的图像点集仿射配准算法相比,所提算法的准确性和稳健性显著提高。A robust affine iterative closest point algorithm is proposed based on a control point consistency constraint. The proposed algorithm establishes an objective function that is constrained by the control points, and the data point set can be affinely registered to a target point set. Furthermore, the nearest point correspondence is established between the data point and target point sets;subsequently, a random sample consensus method is used to select the high-precision shape control points, and the new affine transformation is obtained using an objective function under a control point constraint. The experimental results demonstrate that the accuracy and the robustness of the proposed algorithm are improved significantly when compared with those exhibited by the conventional image point set affine registration algorithms.

关 键 词：图像处理 图像点集配准 仿射配准 仿射迭代最近点 形状控制点 一致性约束 

分 类 号：TN911.37[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]