Abstract
It is a difficult task to estimate the human transition motion without the specialized software. The 3-dimensional (3D) human motion animation is widely used in video game, movie, and so on. When making the animation, human transition motion is necessary. If there is a method that can generate the transition motion, the making time will cost less and the working efficiency will be improved. Thus a new method called latent space optimization based on projection analysis (LSOPA) is proposed to estimate the human transition motion. LSOPA is carried out under the assistance of Gaussian process dynamical models (GPDM); it builds the object function to optimize the data in the low dimensional (LD) space, and the optimized data in LD space will be obtained to generate the human transition motion. The LSOPA can make the GPDM learn the high dimensional (HD) data to estimate the needed transition motion. The excellent performance of LSOPA will be tested by the experiments.
Highlights
3-dimensional (3D) human motion animation is applied in many fields, such as video game and movie
Gaussian process dynamical models (GPDM) can be selected to learn the samples of the two different human motions; the low dimensional (LD) space can be built to find the needed LD data of the transition motion, so that corresponding poses can be generated through the mapping of (9)
The latent space optimization based on projection analysis (LSOPA) is proposed to solve the problem of estimating the human transition motion
Summary
3-dimensional (3D) human motion animation is applied in many fields, such as video game and movie. If there is a method that can estimate the valid human transition motion, the animation making time will cost less, and the work will get easier. LD data will be optimized by LSOPA, so that the valid human transition motion can be generated to achieve the estimation. GPDM is an unsupervised learning model; it can learn the high dimensional data (HD) sample and estimate the new one, but it needs to process the LD data in the LD space. The LSOPA can do this work to process the LD data better and ensure the valid transition motion can be generated. The transition motion consists of many poses, and the poses are all the HD data samples of 3D human model, how to estimate the valid transition motion is a challenged task.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Digital Multimedia Broadcasting
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
