3-D model-based segmentation of videoconference image sequences

Abstract

This paper describes a three-dimensional (3-D) model-based unsupervised procedure for the segmentation of multiview image sequences using multiple sources of information. The 3-D model is initialized by accurate adaptation of a two-dimensional wireframe model to the foreground object of one of the views. The articulation procedure is based on the homogeneity of parameters, such as rigid 3-D motion, color, and depth, estimated for each subobject, which consists of a number of interconnected triangles of the 3-D model. The rigid 3-D motion of each subobject for subsequent frames is estimated using a Kalman filtering algorithm, taking into account the temporal correlation between consecutive frames. Information from all cameras is combined during the formation of the equations for the rigid 3-D motion parameters. The threshold used in the object segmentation procedure is updated at each iteration using the histogram of the subobject parameters. The parameter estimation for each subobject and the 3-D model segmentation procedures are interleaved and repeated iteratively until a satisfactory object segmentation emerges. The performance of the resulting segmentation method is evaluated experimentally