K
Kenji Oka
Researcher at University of Tokyo
Publications - 20
Citations - 914
Kenji Oka is an academic researcher from University of Tokyo. The author has contributed to research in topics: Gesture recognition & Desk. The author has an hindex of 11, co-authored 20 publications receiving 894 citations. Previous affiliations of Kenji Oka include Panasonic.
Papers
More filters
Journal ArticleDOI
Real-time fingertip tracking and gesture recognition
TL;DR: A method for discerning fingertip locations in image frames and measuring fingertip trajectories across image frames is introduced and a mechanism for combining direct manipulation and symbolic gestures based on multiple fingertip motions is proposed.
Journal Article
Real-time tracking of multiple fingertips and gesture recognition for augmented desk interface systems
TL;DR: A fast and robust method for tracking a user's hand and multiple fingertips and gesture recognition based on measured fingertip trajectories for augmented desk interface systems, which is particularly advantageous for human-computer interaction (HCI).
Proceedings ArticleDOI
Real-time tracking of multiple fingertips and gesture recognition for augmented desk interface systems
TL;DR: In this paper, the location of each fingertip is located in each input infrared image frame and correspondences of detected fingertips between successive image frames are determined based on a prediction technique, which is particularly advantageous for human-computer interaction.
Proceedings ArticleDOI
Combining head tracking and mouse input for a GUI on multiple monitors
TL;DR: In this experiment head tracking is used to switch the mouse pointer between monitors and use the mouse to move within each monitor, and users required significantly less mouse movement with the tracking system, and preferred using it, although task time actually increased.
Proceedings Article
Head Pose Estimation System Based on Particle Filtering with Adaptive Diffusion Control
TL;DR: A new tracking system based on a stochastic filtering framework for reliably estimating the 3D pose of a user’s head in real-time and designed to control the difusion factor of a motion model adaptively is proposed.