Object-oriented scene modeling for interpersonal video communication at very low bit-rate

摘要

This paper describes a new approach to very low bit-rate interpersonal visual communication based on a suitable scene model, i.e. a flexible structure adapted to the specific characteristics of the speaker's face. The face model is dynamically adapted to time-varying facial expressions by means of few parameters, estimated from the analysis of the real image sequence, which are used to apply knowledge-based deformation rules on a simplified muscle structure. Facial muscles are distributed in correspondence to the primary facial features and can be activated through the direct stimulation of each individual fiber or, indirectly, by interaction with adjacent stimulated fibers. The analysis algorithms performed at the transmitter to estimate the model parameters are based on feature-oriented operators aimed at segmenting the real incoming frames and at the extraction of the primary facial descriptors. The analysis/synthesis algorithms have been developed on a Silicon Graphics workstation and have been tested on various ‘head-and-shoulder’ sequences: the obtained results are very promising for applications both in videophone coding and in picture animation, where the facial expressions of a synthetic actor is reproduced according to the parameters extracted from a real speaking face.