阶层式三维形状环特征提取方法

doi:10.11772/j.issn.1001-9081.2017112816

计算机应用 ›› 2018, Vol. 38 ›› Issue (6): 1755-1759.DOI: 10.11772/j.issn.1001-9081.2017112816

• 虚拟现实与多媒体计算 • 上一篇下一篇

阶层式三维形状环特征提取方法

左向梅¹, 贾丽姣¹, 韩鹏程²

1. 中国飞行试验研究院试验机设计改装研究部, 西安 710089;
2. 西北工业大学航空学院, 西安 710072

收稿日期:2017-11-30 修回日期:2018-01-03 出版日期:2018-06-10 发布日期:2018-06-13
通讯作者: 左向梅
作者简介:左向梅(1990-),女,陕西蒲城人,工程师,硕士,主要研究方向:计算机图形图像处理、模式识别、人工智能;贾丽姣(1990-),女,陕西韩城人,工程师,硕士,主要研究方向:计算机视觉、图像处理;韩鹏程(1991-),男,江苏泰州人,博士研究生,主要研究方向:计算机视觉、图形图像处理、机器学习。
基金资助:
国家自然科学基金资助项目（61573284）。

Hierarchical three-dimensional shape ring feature extraction method

ZUO Xiangmei¹, JIA Lijiao¹, HAN Pengcheng²

1. Experimental Aircraft Design and Modification Institute, Chinese Flight Test Establishment, Xi'an Shaanxi 710089, China;
2. School of Aeronautics, Northwestern Polytechnical University, Xi'an Shaanxi 710072, China

Received:2017-11-30 Revised:2018-01-03 Online:2018-06-10 Published:2018-06-13
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61573284).

摘要/Abstract

摘要： 针对已有的三维形状局部特征属性单一及缺乏空间结构信息的问题，提出了一种融合三维形状拓扑连接信息的阶层式特征提取框架，并得到具有平移不变性的三维形状环特征。首先，以三维形状底层特征提取为基础，进一步利用等测地线环的方式对特征点的局部区域进行建模，抽象出包含丰富空间几何结构信息的中层特征；然后，利用稀疏编码方式对中层特征进一步概括抽象，进而得到更具区分力和丰富信息的高层特征。将该高层特征与已有的尺度不变的热核描述子（SI-HKS）在三维形状对应和形状检索这两类任务中进行对比，该特征准确率分别提高了24.5个百分点和7.2个百分点。实验结果表明所提特征相较于已有的特征描述符具有更高的分辨率和识别度。

关键词: 三维形状, 局部特征, 稀疏编码, 拓扑连接, 形状检索

Abstract: The existing three-dimensional shape local features are mostly lack of spatial structure information and only contain a single property. In order to solve the problems, a hierarchical feature extraction framework integrating topological connection information of three-dimensional shape was proposed to obtain the three-dimensional shape ring feature with shift invariance. Firstly, based on the low-level feature extraction of a three-dimensional shape, the local region of feature points was modeled by the way of the isometric geodesic ring, which could extract the middle-level feature containing rich spatial geometric structure information. Then, the middle-level feature was further abstracted by using sparse coding to obtain more discriminative high-level feature with abundant information. The obtained high-level feature was compared with the existing Scale Invariant Heat Kernel Signature (SI-HKS) in two tasks of three-dimensional shape correspondence and shape retrieval, and its accuracy was increased by 24.5 percentage points and 7.2 percentage points respectively. The experimental results show that the proposed feature has higher resolution and recognition than the existing feature descriptors.

Key words: three-dimensional shape, local feature, sparse coding, topological connection, shape retrieval

中图分类号:

TP391.4

左向梅, 贾丽姣, 韩鹏程. 阶层式三维形状环特征提取方法[J]. 计算机应用, 2018, 38(6): 1755-1759.

ZUO Xiangmei, JIA Lijiao, HAN Pengcheng. Hierarchical three-dimensional shape ring feature extraction method[J]. Journal of Computer Applications, 2018, 38(6): 1755-1759.

参考文献

[1] HILAGA M, SHINAGAWA Y, KOHMURA T, et al. Topology matching for fully automatic similarity estimation of 3D shapes[C]//Proceedings of the 28th Annual Conference On Computer Graphics And Interactive Techniques. New York:ACM, 2001:203-212.
[2] BRONSTEIN M M, KOKKINOS I. Scale-invariant heat kernel signatures for non-rigid shape recognition[C]//Proceedings of the 2010 IEEE Conference On Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2010:1704-1711.
[3] SHAPIRA L, SHAMIR A, COHEN-OR D. Consistent mesh partitioning and skeletonisation using the shape diameter function[J]. Visual Computer, 2008, 24(4):249-259.
[4] 张洁琳,宿婧,罗钟铉,等.基于热核信号的3D图形的分层匹配方法[J].计算机辅助设计与图形学学报,2014,26(12):2142-2148.(ZHANG J L, SU J, LUO Z X, et al. Hierarchical matching of 3D shape based on heat kernel signature[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(12):2142-2148.)
[5] 阮义彰,童伟淮,潘翔,等.结合热核信号和测地距离的三维模型紧密对齐[J].计算机科学,2015,42(6A):199-202.(RUAN Y Z, TONG W H, PAN X, et al. 3D shape dense correspondence by combining heat kernel and geodesic distance[J]. Computer Science, 2015, 42(6A):199-202.)
[6] 姜巍.三维几何模型的内蕴对称检测技术研究[D].长沙:国防科学技术大学,2013:60-66(JIANG W. Research on key technologies of intrinsic symmetry detection in 3D geometry models[D]. Changsha:National University of Defense Technology, 2013:60-66)
[7] BU S H, HAN P C, LIU Z B, et al. Local deep feature learning framework for 3D shape[J]. Computers & Graphics, 2015, 46(C):117-129.
[8] PEYRÉ G, COHEN L D. Geodesic remeshing using front propagation[J]. International Journal of Computer Vision, 2006, 69(1):145-156.
[9] KIMMEL R, SETHIAN J A. Computing geodesic paths on manifolds[J]. Proceedings of the National Academy of Sciences of the United States of America, 1998, 95(15):8431-8435.
[10] GROSSE R, RAINA R, KWONG H, et al. Shift-invariance sparse coding for audio classification [EB/OL]. [2017-10-16]. http://www.robotics.stanford.edu/~ang/papers/uai07-shiftinvariantsparsecoding.pdf.
[11] KIM V G, LIPMAN Y, FUNKHOUSER T. Blended intrinsic maps [J]. ACM Transactions on Graphics, 2011, 30(4): Article No. 79.
[12] SIDDIQI K, ZHANG J, MACRINI D, et al. Retrieving articulated 3-D models using medial surfaces [J]. Machine Vision and Applications, 2008, 19(4): 261-275.
[13] LEORDEANU M, HEBERT M. A spectral technique for correspondence problems using pairwise constraints [C]// Proceedings of the 2005 Tenth IEEE International Conference on Computer Vision. Piscataway, NJ: IEEE, 2005: 1482-1489.
[14] BRONSTEIN A M, BRONSTEIN M M, GUIBAS L J, et al. Shape google: geometric words and expressions for invariant shape retrieval [J]. ACM Transactions on Graphics, 2011, 30(1): Article No. 1.
[15] SHILANE P, MIN P, KAZHDAN M, et al. The Princeton shape benchmark [C]// Proceedings of the 2004 Shape Modeling International . Washington, DC: IEEE Computer Society, 2004: 167-178.
[16] KAZHDAN M, FUNKHOUSER T, RUSINKIEWICZ S. Rotation invariant spherical harmonic representation of 3D shape descriptors [C]// Proceedings of the 2003 Eurographics/ACM SIGGRAPH Symposium on Geometry Processing. Aire-la-Ville, Switzerland: The Eurographics Association, 2003: 156-164.
[17] JAIN V, ZHANG H. A Spectral approach to shape-based retrieval of articulated 3D models [J]. Computer-Aided Design,2007, 39(5): 398-407.
[18] AGATHOS A, PRATIKAKIS I, PAPADAKIS P, et al. 3D articulated object retrieval using a graph-based representation [J]. Visual Computer, 2010, 26(10): 1301-1319.

阶层式三维形状环特征提取方法

Hierarchical three-dimensional shape ring feature extraction method

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	万源, 张景会, 陈治平, 孟晓静. 基于弹性网和直方图相交的非负局部稀疏编码[J]. 计算机应用, 2019, 39(3): 706-711.
[2]	万源, 张景会, 吴克风, 孟晓静. 基于多层非负局部Laplacian稀疏编码的图像分类[J]. 计算机应用, 2018, 38(9): 2489-2494.
[3]	邹承明, 罗莹, 徐晓龙. 基于多特征组合的细粒度图像分类方法[J]. 计算机应用, 2018, 38(7): 1853-1856.
[4]	王岩, 罗倩, 邓辉. 基于Gibbs抽样的轴承故障诊断方法[J]. 计算机应用, 2018, 38(7): 2136-2140.
[5]	陈晨, 赵建伟, 曹飞龙. 基于四通道卷积稀疏编码的图像超分辨率重建方法[J]. 计算机应用, 2018, 38(6): 1777-1783.
[6]	杨晓玲, 李志清, 刘雨桐. 基于多标签判别字典学习的图像自动标注[J]. 计算机应用, 2018, 38(5): 1294-1298.
[7]	王茜, 陈一民, 丁友东. 复杂环境中基于视觉词袋模型的车辆再识别算法[J]. 计算机应用, 2018, 38(5): 1299-1303.
[8]	王丽芳, 成茜, 秦品乐, 高媛. 基于多通道稀疏编码的非刚性多模态医学图像配准[J]. 计算机应用, 2018, 38(4): 1127-1133.
[9]	王之毅, 毕笃彦, 熊磊, 凡遵林, 张晓瑜. 基于稀疏编码和岭回归的文本图像复原算法[J]. 计算机应用, 2017, 37(9): 2648-2651.
[10]	刘盛清, 孙季丰, 余家林, 宋治国. 基于多尺度特征融合Hessian稀疏编码的图像分类算法[J]. 计算机应用, 2017, 37(12): 3517-3522.
[11]	夏俊, 李映华. 球面凸类图形Delaunay三角剖分再分算法及其收敛性分析[J]. 计算机应用, 2017, 37(12): 3558-3562.
[12]	黄秀杰, 陈靖, 张运超. 基于最小重构误差的优化局部聚合描述符向量图像检索算法[J]. 计算机应用, 2016, 36(6): 1682-1687.
[13]	何华, 李宗春, 李国俊, 阮焕立, 隆昌宇. 散乱点云的自适应α-shape曲面重建[J]. 计算机应用, 2016, 36(12): 3394-3397.
[14]	阮峰, 张辉, 李宣伦. 大输液异物检测图像快速位移补偿方法[J]. 计算机应用, 2016, 36(12): 3442-3447.
[15]	赵晓健, 曾晓勤. 基于稠密光流轨迹和稀疏编码算法的行为识别方法[J]. 计算机应用, 2016, 36(1): 181-187.