Human arm modeling for analysis/synthesis image coding

Abstract

Analysis/synthesis image coding is potentially a powerful technique for compressing scenes dominated by the head-shoulder images, as in a videotelephone scene with a closeup of the human upper-body. In this paper, we propose a novel approach to image coding of the human arm, based on kinematic modeling of the human arm and motion analysis of the head-shoulder image sequences. The main characteristics of this approach are that i) it relies on the assumption that the human arm can be modeled as a kinematic linkage connected by movable joints, ii) it approximates the 3-D kinematic arm motion from the 2-D image velocities, and iii) it synthesizes shoulder image sequences from one frame of texture image, the wire-frame arm model, and estimated kinematic motion. We evaluated our approach in simulations involving a grayscale monocular image sequence of a moving arm.<>