Perceptually optimised sign language video coding

Abstract

Mobile video telephony will enable deaf people to communicate in their own language, sign language. At low bit rates coding of sign language video is challenging due the high levels of motion and the need to maintain good image quality to aid with understanding. This paper presents perceptually optimised coding of sign language video at low bit rates. The proposed optimisations are based on an eye-tracking study that we have conducted with the aim of characterising the visual attention of sign language viewers. Analysis and results of this study and two coding methods, one using MPEG-4 video objects and the second using foveation filtering, are presented. Results with foveation filtering are promising, offering a considerable decrease in bit rate in a manner compatible with the visual attention patterns of deaf people, as these were recorded in the eye tracking study.