Open AccessTracking and Interaction Based on Hybrid Sensing for Virtual Environments
Author(s) -
Jo Dongsik,
Kim Yongwan,
Cho Eunji,
Kim Daehwan,
Kim KiHong,
Lee GilHaeng
Publication year - 2013
Publication title -
etri journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.295
H-Index - 46
eISSN - 2233-7326
pISSN - 1225-6463
DOI - 10.4218/etrij.13.0212.0170
Subject(s) - gyroscope , tracking (education) , computer science , computer vision , match moving , artificial intelligence , acceleration , position (finance) , motion (physics) , inertial measurement unit , motion capture , tracking system , interface (matter) , construct (python library) , engineering , kalman filter , psychology , physics , finance , pedagogy , classical mechanics , economics , programming language , aerospace engineering , bubble , maximum bubble pressure method , parallel computing
We present a method for tracking and interaction based on hybrid sensing for virtual environments. The proposed method is applied to motion tracking of whole areas, including the user's occlusion space, for a high‐precision interaction. For real‐time motion tracking surrounding a user, we estimate each joint position in the human body using a combination of a depth sensor and a wand‐type physical user interface, which is necessary to convert gyroscope and acceleration values into positional data. Additionally, we construct virtual contents and evaluate the validity of results related to hybrid sensing‐based whole‐body tracking of human motion methods used to compensate for the occluded areas.