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 50 条

[31] Automatic reconstruction of 3D human motion pose from uncalibrated monocular video sequences based on markerless human motion tracking
Zou, Beiji
Chen, Shu
Shi, Cao
Providence, Umugwaneza Marie
PATTERN RECOGNITION, 2009, 42 (07) : 1559 - 1571
[32] 3D human skeleton reconstruction from motion image sequence
Zhuang, Yue-Ting
Liu, Xiao-Ming
Pan, Yun-He
Yang, Jun
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design & Computer Graphics, 2000, 12 (04): : 245 - 250
[33] 3D MOTION ESTIMATION FOR 3D VIDEO CODING
Paul, Manoranjan
Gao, Junbin
Anotolovich, Michael
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 1189 - 1192
[34] Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Wei, Wen-Li
Lin, Jen-Chun
Liu, Tyng-Luh
Liao, Hong-Yuan Mark
arXiv, 2022,
[35] Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Wei, Wen-Li
Lin, Jen-Chun
Liu, Tyng-Luh
Liao, Hong-Yuan Mark
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2022, 2022-June : 13201 - 13210
[36] Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video
Wei, Wen-Li
Lin, Jen-Chun
Liu, Tyng-Luh
Liao, Hong-Yuan Mark
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 13201 - 13210
[37] Motion composition of 3D video
Xu, Jianfeng
Yamasaki, Toshihiko
Aizawa, Kiyoharu
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2006, PROCEEDINGS, 2006, 4261 : 385 - 394
[38] 3D Skeleton Estimation and Human Identity Recognition Using Lidar Full Motion Video
Glandon, A.
Vidyaratne, L.
Sadeghzadehyazdi, N.
Dhar, Nibir K.
Familoni, Jide O.
Acton, Scott T.
Iftekharuddin, K. M.
2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
[39] Bridging the gap between detection and tracking for 3D monocular video-based motion capture
Fossati, Andrea
Dimitrijevic, Miodrag
Lepetit, Vincent
Fua, Pascal
2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8, 2007, : 2510 - +
[40] Using Video Motion Vectors for Structure from Motion 3D Reconstruction
Turner, Richard N. C.
Banerjee, Natasha Kholgade
Banerjee, Sean
SIGMAP: PROCEEDINGS OF THE 19TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND MULTIMEDIA APPLICATIONS, 2022, : 13 - 22

← 1 2 3 4 5 →