利用Capped核范数正则化的人体运动捕获数据恢复  

Human Motion Capture Data Recovery Using Capped Nuclear Norm Regularization

作　　者：胡文玉[1] 朱雪芳 易云[1] Hu Wenyu;Zhu Xuefang;Yi Yun(School of Mathematics and Computer Science,Gannan Normal University,Ganzhou 341000;School of Communications and Information,Jiangxi Environmental Engineering Vocational College,Ganzhou 341000)

机构地区：[1]赣南师范大学数学与计算机科学学院,赣州341000 [2]江西环境工程职业学院通讯与信息学院,赣州341000

出　　处：《计算机辅助设计与图形学学报》2023年第8期1184-1196,共13页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(62266002,61863001,61962003,61502107);江西省自然科学基金(20224BAB202004,20202BAB202017)。

摘　　要：结合人体运动数据的低秩性、噪声稀疏性和时序稳定性,将人体运动捕获数据恢复问题建模为低秩矩阵填充问题.不同于传统方法采用核范数作为矩阵秩函数的凸松弛,引入了非凸的矩阵Capped核范数(CaNN).首先,建立基于CaNN正则化的人体运动捕获数据恢复模型;其次,利用交替方向乘子法,结合截断参数自适应学习与(逆)离散余弦傅里叶变换对模型进行快速求解;最后,在CMU数据集和HDM05数据集上,将CaNN模型与经典的TSMC,TrNN,IRNN-Lp和TSPN模型进行对比实验.恢复误差和视觉效果比较结果表明,CaNN能够有效地对失真数据进行恢复,且恢复后的运动序列与真实运动序列逼近度较高.Using the low-rank property of human motion data,the problem of recovering human motion capture data is modeled as a low-rank matrix completion problem.Different from the traditional methods which utilize the nuclear norm as the convex relaxation of rank function,a non-convex matrix Capped nuclear norm(CaNN)is introduced in this paper.Firstly,the recovery model of human motion capture data is established based on the CaNN regularization.Secondly,the model is efficiently solved by using the alternative direction method of multipliers,combined with adaptive learning for the truncated parameter and(inverse)discrete cosine Fourier transform.Finally,the proposed model CaNN is compared with four classical models,i.e.,TSMC,TrNN,IRNN-Lp and TSPN,on CMU dataset and HDM05 dataset.By comparing the recovery error and visual effect,the experimental results show that CaNN has a good ability to recover the corrupted motion data,and the recovered motions can well approximate the true ones.

关 键 词：运动捕获 低秩结构 矩阵填充 Capped核范数 交替方向乘子法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]