计算机工程与应用 ›› 2015, Vol. 51 ›› Issue (11): 182-186.

• 图形图像处理 • 上一篇    下一篇

基于区域离散曲率的三维网格分水岭分割

贾  晖1,2,耿国华1,周明全3,张建刚4   

  1. 1.西北大学 信息科学与技术学院,西安 710127
    2.西安邮电大学 计算机学院,西安 710121
    3.北京师范大学 信息科学与技术学院,北京 100875
    4.西安热工研究院有限公司 电站信息及监控技术部,西安 710032
  • 出版日期:2015-06-01 发布日期:2015-06-12

Watershed 3D mesh segmentation based on regional discrete curvature

JIA Hui1,2, GENG Guohua1, ZHOU Mingquan3, ZHANG Jiangang4   

  1. 1.School of Information Science & Technology, Northwest University, Xi’an 710127, China
    2.School of Computer Science & Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, China
    3.School of Information Science & Technology, Beijing Normal University, Beijing 100875, China
    4.Department of Information and Supervision, Xi’an Thermal Power Research Institute Co Ltd, Xi’an 710032, China
  • Online:2015-06-01 Published:2015-06-12

摘要: 针对离散曲率估计对噪声敏感且特征值计算量大的特点提出了基于区域离散曲率的三维网格分水岭分割算法。寻找三维模型显著特征点;对三维模型进行预分割,确定分割带;在分割带区域上计算离散曲度极值点,利用测地距离和曲度极值点对三维模型进行分水岭分割。算法在分割前无需进行网格去噪,实验结果证明,对主体分支明显的模型具有较高的分割边缘准确度和较快的分割速度。

关键词: 三维模型, 网格分割, 区域离散曲率, 分水岭算法

Abstract: The discrete curvature is sensitive to the noise and heavy computation of feature value. In order to segment the 3D meshes, this paper presents a novel and efficient watershed algorithm which is based on regional discrete curvature. It extracts prominent feature points, pre-segments and then obtains the segment region. It estimates the discrete curvature within the segment region. It utilizes the Gauss curvature as the feature watershed to segment the 3D mesh. This algorithm does not need to wipe off the noise at initial stage, the experimental results show that the proposed algorithm can accurately and frequently yield meaningful borderline which has an evident branch structure.

Key words: 3-dimensional model, mesh segmentation, regional discrete curvature, watershed algorithm