3D motion and skeleton construction from monocular video

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 sequ...

全面介紹

Saved in:
書目詳細資料
Main Authors: Azmi, Nik Mohammad Wafiy, Albakri, Ikmal Faiq, Mohd. Suaib, Norhaida, Mohd. Rahim, Mohd. Shafry, Yu, Hongchuan
格式: Conference or Workshop Item
出版: 2020
主題:
在線閱讀:http://eprints.utm.my/id/eprint/89722/
http://dx.doi.org/10.1007/978-981-15-0058-9_8
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
實物特徵
總結: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.