Monocular camera-based 3D human body pose estimation by Generative Adversarial Network considering joint range of motion represented by quaternion

Monocular camera-based 3D human body pose estimation by Generative Adversarial Network considering joint range of motion represented by quaternion

This study aims to establish a monocular camera-based system that uses a generative adversarial network (GAN) to estimate a 3D pose of a human and his/her orientation relative to the camera from images by considering anatomical knowledge such as segment length and joint range of motion. The proposed...

Full description

Bibliographic Details
Main Authors: Akisue KURAMOTO, Kosuke MIZUKOSHI, Motomu NAKASHIMA
Format: Article
Language:English
Published: The Japan Society of Mechanical Engineers 2023-01-01
Series:Journal of Biomechanical Science and Engineering
Subjects:
monocular camera
3d pose estimation
joint rotation
quaternion
generative adversarial network (gan)
range of motion
segment length
openpose
Online Access:https://www.jstage.jst.go.jp/article/jbse/18/2/18_22-00305/_pdf/-char/en

Internet

https://www.jstage.jst.go.jp/article/jbse/18/2/18_22-00305/_pdf/-char/en

Similar Items