Presentation 2020-09-08
3D Human Pose Estimation for Omnidirectional Camera
Teppei Miura, Shinji Sako,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Sign-language is the natural interactive visual language used by deaf people. Most hearing people, however, do not know sign-language. For the reason, they usually talk through writing or interpreters between hearing and deaf people. A portable sign-language recognition and translation system is necessary for interactive and direct communication in daily use. Sign-language is composed of some elements: handshapes, movements, positions, facial expressions, and peripheral information. We intend to propose a sign-language recognition system using a wearable omnidirectional camera for the input device, which is portable for daily use, and capable of obtaining enough elements for sign-language recognition. As a first step for the system, we research 3D human pose estimation methods for RGB images taken by the wearable omnidirectional camera in this paper. We apply a convolutional neural network (CNN) to estimate 3D poses. The model is evaluated on our dataset that we collect 3D poses and RGB equirectangular images by a wearable omnidirectional camera.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) 3D pose estimation / Omnidirectional camera / Wearable / Sign-language
Paper # WIT2020-7
Date of Issue 2020-09-01 (WIT)

Conference Information
Committee WIT
Conference Date 2020/9/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online meeting
Topics (in Japanese) (See Japanese page)
Topics (in English) Well-being Information Technology, etc.
Chair Daisuke Wakatsuki(Tsukuba Univ. of Tech.)
Vice Chair Shinji Sakou(Nagoya Inst. of Tech.)
Secretary Shinji Sakou(Saitama Industrial Tech. Center)
Assistant Manabi Miyagi(Tsukuba Univ. of Tech.) / Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.)

Paper Information
Registration To Technical Committee on Well-being Information Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) 3D Human Pose Estimation for Omnidirectional Camera
Sub Title (in English) applying for sign-language recognition
Keyword(1) 3D pose estimation
Keyword(2) Omnidirectional camera
Keyword(3) Wearable
Keyword(4) Sign-language
1st Author's Name Teppei Miura
1st Author's Affiliation Nagoya Institute of Technology(NIT)
2nd Author's Name Shinji Sako
2nd Author's Affiliation Nagoya Institute of Technology(NIT)
Date 2020-09-08
Paper # WIT2020-7
Volume (vol) vol.120
Number (no) WIT-161
Page pp.pp.9-14(WIT),
#Pages 6
Date of Issue 2020-09-01 (WIT)