Current PhD research
My research interests include Computer Vision, Computer Graphics and Animation, mainly releated with human motion synthesis and human motion parameterisation. I am particulary interested in reusing 3D video human motion data to create new motions and parameterise them in real time.
Publications
Dan Casas, Margara Tejera, Jean-Yves Guillemaut and Adrian Hilton.Interactive Animation of 4D Performance Capture
IEEE Transactions on Visualization and Computer Graphics.
[DOI] [preprint]
Dan Casas, Margara Tejera, Jean-Yves Guillemaut and Adrian Hilton.4D Parametric Motion Graphs for Interactive Animation
Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games 2012 (I3D'12).
Honorable Mention for the Best Paper Award
[web] [pdf] [video]
Dan Casas, Margara Tejera, Jean-Yves Guillemaut and Adrian Hilton.Parametric Control of Captured Mesh Sequences for Real-Time Animation
Fourth International Conference on Motion in Games 2011 (MIG2011).
Springer Lecture Notes in Computer Science 7060, 242–253, 2011.
[web] [pdf] [video]
Master's Thesis
I did my Master's Thesis during a 1-year stay as a exchange research schoolar at the Robotics Institute of the Carnegie Mellon University, where I joined the Human Sensing Lab. My research was focused in real-time face tracking methods, and supervised by Dr. Fernando de la Torre.
In the thesis you can find the definition of the face tracking problem and the main motivations for the resarchers to keep on studying such scenario. The first part of the thesis is a literature review in which the most well know algorithms related with face detection and face tracking, such as Lucas-Kanade or Viola-Jones, are discussed. The second part is the practical one and it contains the implementation of different real-time face tracking algorithms, each of them optimized for a certain context and compared with all the other methods.
The following videos are just a few examples of the results I achieved.
My complete thesis can be downloaded from the following link:
