Hand gesture video browsing for broadband-enabled HDTVs

Authors:
Arnaud Bernard;Benny Bing
Affiliations:
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA;School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA
Venue:
Sarnoff'10 Proceedings of the 33rd IEEE conference on Sarnoff
Year:
2010

Citing 4
Cited 1

Using Adaptive Tracking to Classify and Monitor Activities in a Site

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
A comparative study of two state-of-the-art sequence processing techniques for hand gesture recognition

Computer Vision and Image Understanding
Hand Gesture Recognition Using Object Based Key Frame Selection

ICDIP '09 Proceedings of the International Conference on Digital Image Processing
A Unified Framework for Gesture Recognition and Spatiotemporal Gesture Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence

TV remote control using human hand motion based on optical flow system

ICCSA'12 Proceedings of the 12th international conference on Computational Science and Its Applications - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents three methods for hand gesture detection and recognition that can be applied to online video browsing. These methods aim at recognizing hand signs and positions using a single webcam, which can in turn, be used to control a broadband-enabled HDTV. The hand gesture can be trained to suit the user preference. We first provide an analysis of pattern matching, histogram back projection, and the use of Fourier's descriptors. These methods achieve good reliability and acceptable resource consumption. We compare these methods with a new method based on H.264 motion vectors that directly analyzes video in the compressed domain. It will be shown that this technique provides a faster and accurate way to recognize motion trajectories that may correspond to letters or alphabets. The extracted gesture or trajectory information can then be used for various multimedia applications, including improving human-TV interaction.