Universiti Teknologi Malaysia Institutional Repository

3D motion and skeleton construction from monocular video

Azmi, Nik Mohammad Wafiy and Albakri, Ikmal Faiq and Mohd. Suaib, Norhaida and Mohd. Rahim, Mohd. Shafry and Yu, Hongchuan (2020) 3D motion and skeleton construction from monocular video. In: 6th International Conference on Computational Science and Technology, ICCST 2019, 29 August 2019 through 30 August 2019, Kota Kinabalu, Malaysia.

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1007/978-981-15-0058-9_8

Abstract

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.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:2D annotation, 3D annotation, convolutional neural network
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computing
ID Code:89722
Deposited By: Yanti Mohd Shah
Deposited On:22 Feb 2021 14:09
Last Modified:22 Feb 2021 14:09

Repository Staff Only: item control page