A video coding system for sign language communication at low bit rates (MA-P6)

Author(s) : Dimitris Agrafiotis (University of Bristol, UK) Nishan Canagarajah (University of Bristol, UK) Dave Bull (University of Bristol, UK) Jim Kyle (University of Bristol, UK) Helen Seers (University of Bristol, UK) Matthew Dye (University of Rochester, USA)

Abstract : The ability to communicate remotely through the use of video as promised by wireless networks and already practiced over fixed networks, is for deaf people as important as voice telephony is for hearing people. Sign languages are visual languages and as such demand good image quality to aid with understanding. In this paper, based on analysis of the viewers perceptual behavior and the video content involved we propose a sign language video coding system using foveated processing, which can lead to bit rate savings without compromising the comprehension of the coded sequence. We verify this claim by the results of an initial comprehension assessment trial of such coded sequences with deaf users / participants.

Menu