基于高斯曲率和向量内积的人体脊柱模型特征点的改进

鱼滨; 惠宇; 武君胜; 张琛; 张田田

doi:10.3788/OPE.20172513.0250

您当前的位置：

首页 >

文章列表页 >

基于高斯曲率和向量内积的人体脊柱模型特征点的改进

信息科学 | 更新时间：2020-08-13

- 基于高斯曲率和向量内积的人体脊柱模型特征点的改进
- Tagging for improving feature points of human spine model by using Gaussian curvature and vector inner product
- 光学精密工程 2017年25卷第10s期页码：250-258
- 作者机构：
  
  1. 西安电子科技大学计算机学院西安,710072
  2. 西北工业大学计算机学院, 西安 710072
  3. 西北工业大学软件与微电子学院, 西安 710072
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目（No.61172147）();国家自然科学基金青年科学基金资助项目（No.61502365）()
- DOI：10.3788/OPE.20172513.0250
  中图分类号： TP394.1
- 收稿日期：2017-06-02，
  
  修回日期：2017-06-20，
  
  纸质出版日期：2017-11-25
- 稿件说明：
移动端阅览
鱼滨, 惠宇, 武君胜等. 基于高斯曲率和向量内积的人体脊柱模型特征点的改进[J]. 光学精密工程, 2017,25(10s): 250-258

YU Bin, HUI Yu, WU Jun-sheng etc. Tagging for improving feature points of human spine model by using Gaussian curvature and vector inner product[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 250-258
鱼滨, 惠宇, 武君胜等. 基于高斯曲率和向量内积的人体脊柱模型特征点的改进[J]. 光学精密工程, 2017,25(10s): 250-258 DOI： 10.3788/OPE.20172513.0250.

YU Bin, HUI Yu, WU Jun-sheng etc. Tagging for improving feature points of human spine model by using Gaussian curvature and vector inner product[J]. Editorial Office of Optics and Precision Engineering, 2017,25(10s): 250-258 DOI： 10.3788/OPE.20172513.0250.

摘要

针对脊椎结构的复杂性和医学图像采样数据量庞大的问题，提出了一种利用高斯曲率和向量特征改进人体脊柱模型特征点的标注方法，该方法根据模型上某点局部邻域内各点的高斯曲率值和向量内积来动态调整手动标注点的物理坐标。首先，利用三维重建和网格划分生成人体脊椎三维网格模型；然后，手动拾取模型上一点作为初始拾取点，以极小半径R的球形空间作为拾取点的最大近似邻域，在此基础上求出点邻域内所有顶点的高斯曲率绝对值；最后，选取上述高斯曲率值中较大的

个点，分别求取这

个点与初始拾取点之间的向量内积，进而求出

个点中与初始拾取点间夹角角度最小的点，从而将初始拾取点坐标修正为上述夹角角度最小点的物理坐标。该方法在确保取得邻域内尽可能大的高斯曲率值的同时，可以使标记结果更趋近于真实的特征点，实验结果表明，该方法定位脊椎三维模型特征点的准确性约提高29%，且该方法针对脊椎模型的平滑区域具有较好的标注效果。

Abstract

A tagging method for improving feature points of human spine model by using Gauss curvature and the vector feature was proposed in the thesis to dynamically adjust physical coordinates of tagging points based on Gauss curvature values and vector inner products of various points located in local neighborhood in this model. Three-dimensional reconstruction and mesh dividing was used to generate 3D mesh model of thehuman spine; and then

a point in manual pick-up model was chosen as the initial pickup point. Spherical space with minimal radius R was regarded as the maximum approximate neighborhood of the pickup point

based on which absolute values of Gauss curvature for all vertexes in the neighborhood of the pickup point were calculated;

points with larger values from above Gauss curvature values were selected to calculate vector inner product between these n points and initial pickup point and further calculate the point from these points which had the minimum included angle with the initial pickup point

finally

coordinate of the initial pickup point would be corrected to the physical coordinate of the point which had the minimum included angle. The method makes sure that Gauss curvature value taken from the neighborhood is the largest possible value

it can make tagging results closer to the real feature pointat the same time. Experimental results show that the method improves the accuracy of positioning feature point of spinal 3D image by about 29%

besides

relatively good tagging results can be obtained by the method for smooth region of the spine model.

关键词

Keywords

references

SMITH S M,BRADY J M, SUSAN. A new approach to low level image processing[J]. Internationaljournal of computer vision,1997,23(1):45-78.

LOWE D G. Distinctive Image Features from Scale-Invariant Keypoints[J]. Internationaljournal of computer vision,2004,60(2):91-110.

李康,尚鹏,耿国华,等. 基于深度图像的人脸模型特征点自动标定[J]. 计算机科学,2014,41(4):287-291. LI K, SHANG P, GENG G H, et al.. Automatic calibration of feature points based on depth image[J]. Computer Science, 2014,41(4):287-291.(in Chinese)

刘倩,耿国华,周明全,等. 基于三维点云模型的特征线提取算法[J]. 计算机应用研究,2013,30(3):933-937. LIU Q, GENG G H, ZHOU M Q, et al.. Feature line extraction algorithm based on 3D point cloud model[J]. Application Research of Computers, 2013,30(3):933-937.(in Chinese)

徐毅. 基于高斯曲率极值点的散乱点云数据特征点提取[J]. 系统仿真学报,2008,20(9):2341-2344. XU Y. Feature point extraction of scattered point cloud data based on Gaussian curvature extreme point point[J]. Journal of System Simulation, 2008,20(9):2341-2344.(in Chinese)

韩霜. 三维脊椎模型特征点标注的研究与实现[D].西安:西安电子科技大学,2013. HAN SH. Research and implementation of tagging three-dimensional model of the spine with feature points[D].Xi'an:Xidian University,2013(in Chinese)

Jing,Simon Baker,Iain Matthew, Takeo Kanade.Real-time combined 2D+3D active appearance model[J]. Proceeding of the 2004 IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition,200427(2):535-542.

李华明. 基于中国人脸面貌形态学特征的人脸姿态估计方法研究[D]. 西北大学, 2005. LI H M. Study on face phenomenon estimation method based on morphological features of chinese face facsimile[D]. Northwest University, 2005.(in Chinese)

谢易辰,陈健, 等. 三维特征点距离特征集合求交匹配方法[J]. 红外与激光工程, 2014(08).25-31. XIE Y CH,CHEN J, et al..Distance feature set intersection for 3D feature matching.[J]. Infrared and Laser Engineering, 2014(08).25-31. (in Chinese)

王澜,孙博,等. 一种基于共线特征点的线阵相机内参标定方法[J]. 红外与激光工程, 2015(06).134-140. WANG L,SUN B, et al..A novel method for calibrating intrinsic parameters of linear array cameras based on collinear feature points.[J]. Infrared and Laser Engineering, 2015(06).134-140. (in Chinese)

陈维桓. 微分几何. 北京大学出版社. 2006,06,01.CHEN W H. Differential geometry. Peking University Press. 2006,06,01. CHEN W Y. Differential Geometry. Peking University Press. 2006,06,01.CHEN W H. Differential geometry. Peking University Press. 2006,06,01.(in Chinese)

浏览量

421

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据