3-D MOTION ESTIMATION OF HUMAN HEAD FOR MODEL-BASED IMAGE-CODING

Model-based image coding applied to interpersonal communication achiev es very low bit-rate image transmission. To accomplish it, accurate th ree-dimensional (3-D) motion estimation of a speaker is necessary. A n ew method of 3-D motion estimation is presented, consisting of two ste ps. In the first, facial contours and feature points of a speaker are extracted using filtering and Snake algorithms. Five feature points on a speaker's facial image are tracked between consecutive picture fram es, which gives 2-D motion vectors of the feature points. Then, in the second step, the 3-D motion of a speaker's head is estimated using a three-layered neural network model, after training with many possible motion patterns of the human head using an existing 3-D general shape model. Experimental results show that our method not only achieves goo d results but is also more robust than existing methods, even when the motion of an object is rather large or complicated. Accurately estima ted 3-D motion parameters can realise image transmission at a very low bit rate.