We address the task of unconstrained 2D and 3D human pose estimation in single images. Both have a wide field of applicability. This ranges e.g. from video indexing over security and safety applications to entertainment purposes and marker less motion capture. The recovery of a human pose in a single image, however, is still a challenging problem. Highly articulated human poses, cluttered background and partial or complete occlusions require robust methods. The absence of a temporal model makes this particularly challenging.

Our research goal is to develop robust algorithms for this task. We aim to design methods that are on the one hand generic and robust, but on the other hand try to make use very simple techniques so that the overall complexity of the models stays low. This is extremely important in order to reach real time capable pose estimation in images.

For more information please contact  Thomas Greif.

References:

• Thomas Greif, Debabrata Sengupta, Rainer Lienhart. Monocular 3D Human Pose Estimation by Classification. IEEE International Conference on Multimedia and Expo 2011 (ICME11), Barcelona, July 2011. [ PDF ]
• Thomas Greif and Rainer Lienhart. A kinematic model for Bayesian tracking of cyclic human motion. IS&T/SPIE Electronic Imaging, San Jose, USA, January 2010. [ PDF ]

Software:

KAET (Kinect Annotation and Evaluation Tool)