最小特征值的迭代非刚体三维射影重建方法  

Iteration Projection Reconstruction Method for 3D Non-Rigid Based on Minimal Eigenvalue

作　　者：裘国永[1,2] 刘静娜 刘中华[3] 彭亚丽[1,2] 刘侍刚[1,2] QIU Guo-yong LIU Jing-na LIU Zhong-hua PENG Ya-li LIU Shi-gang(Key Laboratory of Modern Teaching Technology-,Ministry of Education,Xi＇ an, Shaanxi 710062, China Engineering Laboratory of Teaching Information Technology of Shaanxi Province ,Xi ＇ an, Shaanxi 710119, China College of Information Engineering, Henan University of Science and Technology,Luoyang, Henan 471023, China)

机构地区：[1]现代教学技术教育部重点实验室,陕西西安710062 [2]陕西省教学信息技术工程实验室,陕西西安710119 [3]河南科技大学电子信息工程学院,河南洛阳471023

出　　处：《电子学报》2017年第5期1211-1217,共7页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61402274;No.61672333;No.61461025;No.61202314;No.41471280;No.61501286;No.U1504610);陕西省工业科技攻关项目(No.2016GY-081);陕西省重点科技创新团队计划项目(No.2014KTC-18);中国博士后特别资助项目(No.2014T70937);陕西师范大学中央高校基本科研业务费项目(No.GK201402040);陕西师范大学学习科学交叉学科培育计划资助

摘　　要：为了从图像序列中重建出非刚体三维射影重建,本文提出了一种最小特征值的迭代非刚体射影重建方法.该方法利用所有的图像点和深度因子组成一个低秩图像矩阵的特性,将投影求解转化为矩阵特征值及特征向量的求解,迭代地求解深度因子,实现非刚体的三维射影重建.该方法能够保证算法能够收敛到全局最优解.模拟实验和真实实验结果表明,本文方法具有收敛性速度快、误差小等优点.To obtain 3D non-rigid projective reconstruction from an image sequence, an iteration projection reconstruction method for 3D non-rigid based on minimal eigenvalue is presented. Based on the characteristic that all the image points and the depth factors constitute a low rank image matrix, the method replaces projection solution by eigenvalue and eigenvector solution. Then we can obtain the depth factors by iteration. Finally, the 3D non-rigid projective reconstruction is realized. The method can guarantee to converge to the global optimal solution. The experiments with both simulate and real data show that the proposed method has the advantages of fast convergence speed and small error.

关 键 词：非刚体 射影重建 特征值 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]