Publicado em: 13/09/2010

Schubert Carvalho palestra no INF

O pós-doc Schubert Carvalho ministra na próxima quinta-feira, 16/09, as 10h30, palestra no auditório do prédio novo.

Talk: Data-Driven Constraint-Based Motion Editing

Abstract:

The growth of motion capture systems has contributed to the proliferation of human motion database, mainly because human motion is important in many applications, ranging from games entertainment and films to sports and medicine. However, the various captured motions normally require specific needs. Consequently, modifying and reusing these motions in new situations – for example, retargeting it to a new environment – became an increasing area of research known as motion editing. In the last few years, human motion editing has become one of the most active research areas in the field of computer animation.

In this talk, I will introduce and discuss a method for interactive human motion editing. Essentially, the technique is based on the mathematical connections between a linear motion model such as Principal Component Analysis (PCA) and a Prioritized Inverse Kinematics (PIK) technique. PCA is used as a first stage of preprocessing to reduce the dimensionality of the database to make it tractable, to encapsulate an underlying motion pattern and to bound IK solutions within the space of natural-looking motions. PIK allows the animator to manipulate constraints with different priorities while interactively editing an animation. The priority strategy ensures that a higher priority task is not affected by other tasks of lower priority.

The main contribution of this work is the development of a Low-dimensional Prioritized Inverse Kinematics (LPIK) technique that handles user constraints within a low-dimensional motion space – also known as the latent space. By construction, it is sufficient to constrain a single frame with LPIK to obtain a natural movement enforcing the intrinsic motion flow.  Moreover, the method offers the compelling advantage that it is well suited for characters with large number of degrees of freedom (DoFs). This is one of the limitations of IK methods that perform optimizations in the joint space. In addition, the proposed method still provides faster deformations and more natural-looking motion results compared to goal-directed constraint-based methods found in the literature.

In the end, it will be shown some experiments used to evaluate and validate (both qualitatively and quantitatively) the benefits of the proposed method. And future trends of my research.

Short Bio:

In December 2009, he received his Ph.D. at the Swiss Federal Institute of Technology, Lausanne (EPFL).  He has M.Sc. and B.S degrees both in Computer Science from the Institute of Computing – UNICAMP – and Federal University of Pará, respectively. Since July 2010, he is a Post-Doctoral fellow at Federal University of Rio Grande do Sul. His major topics of research involve the development of mathematical models for human motion modeling, editing and synthesis with applications in computer animation, robotics and brain computer interfaces.