It is a difficult task to estimate the human transition motion without the specialized software. The 3-dimensional (3D) human\nmotion animation is widely used in video game, movie, and so on. When making the animation, human transition motion is\nnecessary. If there is a method that can generate the transition motion, the making time will cost less and the working efficiency\nwill be improved.Thus a new method called latent space optimization based on projection analysis (LSOPA) is proposed to estimate\nthe human transition motion. LSOPA is carried out under the assistance of Gaussian process dynamical models (GPDM); it builds\nthe object function to optimize the data in the low dimensional (LD) space, and the optimized data in LD space will be obtained\nto generate the human transition motion.The LSOPA can make the GPDM learn the high dimensional (HD) data to estimate the\nneeded transition motion.The excellent performance of LSOPA will be tested by the experiments.
Loading....