3D pose estimation with an Ultra-wide fisheye camera on the chest

We are interested in utilizing egocentric view from a wearable cam- era and are working on MonoEye system, a novel system to estimate the wearer’s motion using a chest-mounted camera equipped with an ultra-wide fisheye lens. Because our system has a wide field of view, it provides a balanced capacity of recognizable pose types and broad egocentric view. The prototype deep neural network estimates camera wearer’s 3D pose and acquires motion without complex configuration like conventional motion capture systems.

Papers:

  • Dong-Hyun Hwang, Kohei Aso, and Hideki Koike. MonoEye: Monocular Fisheye Camera based 3D Human Pose Estimation, IEEE VR 2019, poster, in press.
  • Dong-Hyun Hwang, Kohei Aso, and Hideki Koike. Toward human motion capturing with an ultra-wide fisheye camera on the chest. The First Workshop on Human Augmentation and Its Applications, colocated with IEEE VR 2019, in press.
  • Kohei Aso, Dong-Hyun Hwang, Hideki Koike. Generating Synthetic Humans for Learning 3D Pose Estimation, The First Workshop on Human Augmentation and Its Applications, colocated with IEEE VR 2019, in press.