作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 图形图像处理 • 上一篇    下一篇

基于粒子滤波器算法的特征标记点匹配

李晓捷 a,李光旭 b   

  1. (天津工业大学 a.纺织学院; b.电子与信息工程学院,天津 300387)
  • 收稿日期:2015-03-09 出版日期:2016-02-15 发布日期:2016-01-29
  • 作者简介:李晓捷(1979-),女,讲师、硕士,主研方向为计算机图形学;李光旭,讲师、博士。
  • 基金资助:
    天津市高等学校科技发展计划基金资助项目“基于RGBD深度传感器的三维人体点云数据处理关键技术”(20130324);天津市应用基础与前沿技术研究计划基金资助项目“基于医学图像的器官形状统计图谱的构建”(14JCYBJC42300)。

Characteristic Marked Point Matching Based on Particle Filter Algorithm

LI Xiaojie  a,LI Guangxu  b   

  1. (a.School of Textile; b.School of Electronics and Information Engineering,Tianjin Polytechnic University,Tianjin 300387,China)
  • Received:2015-03-09 Online:2016-02-15 Published:2016-01-29

摘要: 利用等间隔方法在物体表面标定特征标记点构成训练样本集,所获得的统计形状模型质量较低。针对该问题,提出一种基于粒子滤波器算法的特征标记点匹配算法。通过球面保角映射将三维表面映射到二维变量化空间,并利用粒子滤波器算法框架将物体表面局部几何特征量和整体空间结构特征相结合,实现特征点的最优匹配。实验结果表明,与利用等间隔方法相比,该算法获得的统计形状模型具有更高的通用性和专一性。

关键词: 统计形状模型, 点分布模型, 特征点匹配, 表面映射, 粒子滤波器

Abstract: Groupwise surface correspondence is the crucial step to construct the Statistical Shape Model(SSM).However,the quality of the models using the equally-placed landmarks method is not sufficient.Aiming at this problem,this paper proposes a novel correspondence method using particle filte algorithm.All the 3D training surfaces are mapped to a unified spherical parameter space based on the spherical conformal mapping at first.The corresponding parts of the surfaces can be found according to the local geometric characters as well as the global structures,which can be integrated by the frameworks of particle filters.Experimental results illustrate that compared with the equally-placed landmarks method,the SSM models obtained by proposed method can perform well on the general ability and the specific ability.

Key words: Statistical Shape Model(SSM), Point Distribution Model(PDM), characteristic point matching, surface mapping, particle filter

中图分类号: