基于模糊形状上下文与局部向量相似性约束的配准算法  

Registration Algorithm Based on Fuzzy Shape Context and Local Vector Similarity Constraint

作　　者：马新科 杨扬[1,2] 杨昆[1,2] 罗毅[1,2] MA Xin-Ke;YANG Yang;YANG Kun;LUO Yi(Information Science and Technology,Yunnan Normal University,Kunming 650500;The Engineering Research Center of Geographic Information System Technology in Western China of Ministry of Education of China,Kunming 650500)

机构地区：[1]云南师范大学信息学院,昆明650500 [2]西部资源环境地理信息技术教育部工程研究中心,昆明650500

出　　处：《自动化学报》2020年第2期342-357,共16页Acta Automatica Sinica

基　　金：国家自然科学基金项目(41661080);云南省万人计划青年拔尖人才;云南省大学生创新创业训练计划项目(61)资助~~

摘　　要：非刚性点集配准研究是模式识别领域的一项重要基础研究.本文在当前流行的非刚性点集配准算法的基础上提出了两个主要贡献:1)模糊形状上下文(Fuzzy shape context, FSC)特征;2)基于局部向量特征的局部空间向量相似性约束项.本文首先进行基于特征互补的对应关系评估,在这一步骤中定义了模糊形状上下文特征,然后基于模糊形状上下文特征差异和全局特征差异设计了特征互补的高斯混合模型.其次,进行基于约束互补的空间变化更新.在这一步骤中,定义了局部向量特征,建立了局部空间向量相似性约束项.本文算法通过使用特征互补的高斯混合模型进行对应关系评估,并将配准问题转化为可以用期望最大化(Expectation maximization, EM)算法解决的参数优化问题,通过创建包含局部空间向量相似性约束项的能量方程优化了空间变换更新.本文首先测试了模糊形状上下文特征的检索率,然后采用公开数据集测试了算法在点集配准与图像配准的性能.在与当前流行的十种算法的对比实验中,本文算法均给出了精确的配准结果,并在大部分实验中精度超过了当前流行算法.Non-rigid point set registration is an essential research in pattern recognition. Two main contributions are presented based on the current popular non-rigid point set registration algorithm in this paper: 1) Fuzzy shape context feature 2) Local spatial vector similarity constraints based on local vector feature. The correspondence of complementary of features is evaluated, firstly. At the same time, a fuzzy shape context(FSC) feature is defined and the Gaussian mixture model based on the fuzzy shape context distance and the global feature distance is designed. The spatial transformation of complementary of constraint is updated, secondly. Meanwhile, a local vector feature is defined and the local spatial vector similarity constraint based on local vector feature is built. The proposed algorithm estimates correspondence by using the Gaussian mixture model of complementary of feature. The proposed algorithm updates parameters of transformation by using the expectation maximization algorithm, and completes transformation updating by building energy function that has local spatial vector similarity constraints. Firstly, the retrieval rate of FSC is tested. The performance of point set registration and image registration of the proposed algorithm was tested by using public data sets, secondly. In the comparison experiments of currently popular 10 algorithms, accurate registration results of the proposed algorithm where acquired, and surpassed the popular algorithms in most of the registration precision.

关 键 词：非刚性点集配准 高斯混合模型 模糊形状上下文特征 局部向量特征 局部空间向量相似性约束 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]