3D Motion and Skeleton Construction from Monocular Video

被引：0

作者：

Azmi, Nik Mohammad Wafiy ^{[1
]}

Albakri, Ikmal Faiq ^{[1
]}

Suaib, Norhaida Mohd ^{[1
]}

Rahim, Mohd Shafry Mohd ^{[1
]}

Yu, Hongchuan ^{[2
]}

机构：

[1] Univ Teknol Malaysia, Fac Engn, Sch Comp, Johor Baharu, Malaysia

[2] Bournemouth Univ, Natl Ctr Comp Animat, Poole, Dorset, England

来源：

COMPUTATIONAL SCIENCE AND TECHNOLOGY (ICCST 2019) | 2020年 / 603卷

基金：

欧盟地平线“2020”;

关键词：

Convolutional Neural Network; Human Mesh Recovery; 2D annotation; 3D annotation; Maya; Maya Standalone; HIK; Part-affinity;

D O I：

10.1007/978-981-15-0058-9_8

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We describe 3D motion construction as a framework for constructing a 3D motion and skeleton using a monocular video source (2D video). The processes include 3 main phases which involved in generating ground truth 2D annotation using OpenPose, generating the mesh and 3D matrices of person in the sequences of images based on 2D annotation and bounding box and lastly using the matrices to create a HIK 3D skeleton in a standalone Maya application. For the process, we highly relied on the 2D annotation using Convolution Neural Network. We demonstrate our result using a video of Malaysia Traditional Dance called zapin.

引用

页码：75 / 84

页数：10

共 19 条

[1] Andriluka M, 2009, PROC CVPR IEEE, P1014, DOI 10.1109/CVPRW.2009.5206754
[2] 3D Human Pose Estimation from RGB plus D Images with Convolutional Neural Networks
Cai, Yiheng
Wang, Xueyan
Kong, Xinran
[J]. 2018 2ND INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING AND BIOINFORMATICS (ICBEB 2018), 2018, : 64 - 69
[3] Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Cao, Zhe
Simon, Tomas
Wei, Shih-En
Sheikh, Yaser
[J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1302 - 1310
[4] Human Pose Estimation using Body Parts Dependent Joint Regressors
Dantone, Matthias
Gall, Juergen
Leistner, Christian
Van Gool, Luc
[J]. 2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 3041 - 3048
[5] REPRESENTATION AND MATCHING OF PICTORIAL STRUCTURES
FISCHLER, MA
ELSCHLAGER, RA
[J]. IEEE TRANSACTIONS ON COMPUTERS, 1973, C 22 (01) : 67 - 92
[6] Habibie I, 2019, EXPLICIT 2D FEATURES
[7] hen X. C, 2016, ADV NEURAL INFORM PR, P1736
[8] Karlinsky L, 2012, LECT NOTES COMPUT SC, V7574, P326, DOI 10.1007/978-3-642-33712-3_24
[9] Li MP, 2018, INT C PATT RECOG, P115, DOI 10.1109/ICPR.2018.8546194
[10] Stacked Hourglass Networks for Human Pose Estimation
Newell, Alejandro
Yang, Kaiyu
Deng, Jia
[J]. COMPUTER VISION - ECCV 2016, PT VIII, 2016, 9912 : 483 - 499

← 1 2 →