Real-time 3D hand-computer interaction: optimization and complexity reduction

Authors:
Jonas Fredriksson;Sven Berg Ryen;Morten Fjeld
Affiliations:
Chalmers University of Technology, Sweden;Chalmers University of Technology, Sweden;Chalmers University of Technology, Sweden
Venue:
Proceedings of the 5th Nordic conference on Human-computer interaction: building bridges
Year:
2008

Citing 4
Cited 2

CONDENSATION—Conditional Density Propagation forVisual Tracking

International Journal of Computer Vision
Hand tracking for low powered mobile AR user interfaces

AUIC '05 Proceedings of the Sixth Australasian conference on User interface - Volume 40
Fast stochastic optimization for articulated structure tracking

Image and Vision Computing
Smart particle filtering for high-dimensional tracking

Computer Vision and Image Understanding

Real-time 3D markerless multiple hand detection and tracking for human computer interaction applications

Proceedings of the 9th ACM SIGGRAPH Conference on Virtual-Reality Continuum and its Applications in Industry
A glove for tapping and discrete 1D/2D input

Proceedings of the 2012 ACM international conference on Intelligent User Interfaces

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a low-cost method for enabling 3D hand-computer interaction. The method, accompanied by a system, uses the frame capturing functionality of a single consumer-grade webcam. Our recent work has been focused on examining and realizing a less complex system. The presented method reduces the tracking effort to only one reference marker: a color-coded bracelet that helps locate the part of the captured frame containing the user's hand. The located area contains all the information needed to extract hand rotation and finger angle data. To facilitate hand feature extraction, we have outfitted the user's hand with a specially coded glove. The glove is equipped with two square palm markers, a marker on either side of the hand, and five distinctly shaded finger sheaths. We believe that an approach that only tracks only one marker will be more efficient than similar methods that track each finger separately. The method is further simplified by using spatial properties, drawn from physiological characteristics of the human hand, to limit the areas considered by the algorithm. Some challenges regarding webcam limitations may arise when attempting to carry this method into effect, including problems related to image noise and limited image- and color-resolution. Overlapping hands and fingers, hand positioning outside the field of view, and interference by local light sources are other exigent factors to consider.