3D Motion Estimation of Human Head by Using Optical Flow

Abstract

The paper deals with the new algorithm of estimation of large 3D motion of the human head by using the optical flow and the model Candide. In the algorithm prediction of 3D motion parameters in a feedback loop and with multiple iterations was applied. The prediction of 3D motion parameters does not require creating of the synthesized frames but directly uses the frames of input videosequence. Next the algorithm does not need extracting of feature points inside the frames because they are given by the vertices of the used calibrated model Candide. As achieved experimental results show, the iteration process in prediction of 3D motion parameters increased the accuracy of estimation above all the large 3D motion. Such a way the estimation error is decreased without its accumulation in long videosequence. Finally the experimental results show that for 3 iterations a state of saturation was achieved what means that by next increasing of the number of iterations practically no significant increasing of the accuracy of estimation of 3D motion parameters is occurred.