一种透视投影下的非刚体迭代重构方法  

An Iterative Non-rigid Reconstruction Method under Perspective Projection

在线阅读下载全文

作  者:戴龙利 曹蓉蓉[1] 阮宗才[1,2] 

机构地区:[1]东南大学学习科学研究中心,江苏南京210000 [2]东南大学儿童发展与学习科学教育部重点实验室,江苏南京210000

出  处:《计算机技术与发展》2017年第8期16-19,共4页Computer Technology and Development

基  金:全国教育科学规划教育部重点课题(GQA106013);江苏省高校基本科研业务费基础科研扶持项目(2242016K40040)

摘  要:透视投影下的非刚体三维重构中既存在着非刚体形变也存在着透视形变,同时区分两种形变是比较困难的。大多数非刚体三维重构算法通常进行了简化,只考虑正交投影下的非刚体重构。为了解决透视投影下的非刚体重构问题,将基于形状基的EM算法和仿射迭代方法进行有机结合,提出了一种适用于透视投影的新算法。该算法利用EM算法可解决数据点丢失问题的优势以及仿射迭代方法结果较为精确的优点,可提高计算的鲁棒性和重构效果。为验证算法的有效性,选择5 000帧面部表情连续变化的Frank图像序列进行了迭代重构仿真实验。实验结果表明,所提出算法在透视投影模型下具有较好的鲁棒性以及重构效果,能准确地实现动态场景下对人脸的非刚体三维结构重构。Non-rigid three-dimensional reconstruction under perspective projection has both non-rigid deformation and perspective de- formation, and it is difficult to distinguish them. Most of the non-rigid three-dimensional reconstruction algorithm is usually simplified, only considering the non-rigid body reconstruction in orthogonal projection. In order to solve the problem of non-rigid body reconstruc- tion in perspective projection, after combination of the EM algorithm based on shape basis and the affine iterative method, a new algorithm for perspective projection is proposed. It uses the advantage of EM algorithm that can solve the problem of data point loss and of affine it- erative method that is more accurate and thus can improve the robustness and reconstruction effect. In order to its effectiveness, an iterative reconstruction simulation experiment has been performed by selecting 5 000 consecutive Frank images with facial expressions, which indi- cates that it has good robustness and reconstruction effect under the perspective projection model, and can accurately reconstruct the non- rigid three-dimensional structure of human face under dynamic scene.

关 键 词:透视投影 非刚体 形状基 三维运动重构 

分 类 号:TP301[自动化与计算机技术—计算机系统结构]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象