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

[21] Reconstruction of Personalized 3D Face Rigs from Monocular Video
Garrido, Pablo
Zollhoefer, Michael
Casas, Dan
Valgaerts, Levi
Varanasi, Kiran
Perez, Patrick
Theobalt, Christian
ACM TRANSACTIONS ON GRAPHICS, 2016, 35 (03):
[22] Neural Capture of Animatable 3D Human from Monocular Video
Te, Gusi
Li, Xiu
Li, Xiao
Wang, Jinglu
Hu, Wei
Lu, Yan
COMPUTER VISION - ECCV 2022, PT VI, 2022, 13666 : 275 - 291
[23] Joint Semantic Segmentation and 3D Reconstruction from Monocular Video
Kundu, Abhijit
Li, Yin
Dellaert, Frank
Li, Fuxin
Rehg, James M.
COMPUTER VISION - ECCV 2014, PT VI, 2014, 8694 : 703 - 718
[24] Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints
Mahjourian, Reza
Wicke, Martin
Angelova, Anelia
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 5667 - 5675
[25] Video-Based Motion Capturing for Skeleton-Based 3D Models
Shih, Liang-Yu
Chen, Bing-Yu
Wu, Ja-Ling
ADVANCES IN IMAGE AND VIDEO TECHNOLOGY, PROCEEDINGS, 2009, 5414 : 748 - 758
[26] Structure and motion of curved 3D objects from monocular silhouettes
Vijayakumar, B
Kriegman, DJ
Ponce, J
1996 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1996, : 327 - 334
[27] 3D Human Motion Capture from Monocular Image Sequences
Wandt, Bastian
Ackermann, Hanno
Rosenhahn, Bodo
2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2015,
[28] 3D Reconstruction of Human Motion from Monocular Image Sequences
Wandt, Bastian
Ackermann, Hanno
Rosenhahn, Bodo
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (08) : 1505 - 1516
[29] Learning monocular 3D reconstruction of articulated categories from motion
Kokkinos, Filippos
Kokkinos, Iasonas
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 1737 - 1746
[30] Human Motion Synthesis from 3D Video
Huang, Peng
Hilton, Adrian
Starck, Jonathan
CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4, 2009, : 1478 - 1485

← 1 2 3 4 5 →