TNT logo
   

Pose Tracking and Motion Capture Test Sequences

TNT members involved in this project:
Prof. Dr.-Ing. Bodo Rosenhahn

Background

Due to several requests and interest of other research groups on our image sequences we use for model driven tracking, we decided to make them freely available for your own tests and experiments. The sequences (usually) contain the images, projection matrix(es), 3D model and pose init (as 4x4 matrix and a list of joint angles (optional).
To obtain a copy, please send an email to Prof. Rosenhahn with further information about you and your work. Please understand that we can only provide the data to you if you are a senior project manager or senior researcher at your institution.
If you use one of the image sequences or the provided data, the below TPAMI-paper or CVPR-09-paper and this webpage should be cited within your publication.
If you use this dataset and want to have your publication listed here, please drop us a note.
Please note that you are not allowed to pass the data to a third party without prior permission.

Approach

Sequences of the CVPR-09-paper

Indoor-Freeclimbing (images, projection matrices for each frame, surface mesh, 4 moving cameras)
Outdoor-dancing in a Halfpipe (images, projection matrices for each frame, surface mesh, 4 moving cameras)
Outdoor Running and Jumping (images, projection matrices for each frame, surface mesh, 4 moving cameras)
Sequences of the TPami-09-paper
Turntable sequences: Two rigid objects are placed on a turntable and performing a 360 degrees rotation. The y-angle of the estimated motion is a good indicator for a quantitative error analysis
Stereo-TeaBox (with occlusions) and Puncher-sequence with cluttered background
TeaBox and TeaPot-sequences with cluttered background
Kinematic chains: Upper Body, Lower Body in an indoor setup.
Kinematic chains: Full Body motions of sporting activities in an outdoor setup.

References

[1] Thomas Brox, Bodo Rosenhahn, Juergen Gall, Daniel Cremers, Combined Region- and Motion-based 3D Tracking of Rigid and Articulated Objects, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009 (to appear)

[2] N. Hasler, B. Rosenhahn, T. Thormählen, M. Wand, J. Gall, H.-P. Seidel: Markerless Motion Capture with Unsynchronized Moving Cameras, IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), Miami Beach, Florida, June 2009 (accepted).