Spatio-temporal motion tracking with unsynchronized cameras

We present a new spatio-temporal method for markerless motion capture. We reconstruct the pose and motion of a character from a multi-view video sequence without requiring the cameras to be synchronized and without aligning captured frames in time. By formulating the model-to-image similarity measure as a temporally continuous functional, we are also able to reconstruct motion in much higher temporal detail than was possible with previous synchronized approaches. By purposefully running cameras unsynchronized we can capture even very fast motion at speeds that off-the-shelf but high quality cameras provide.

• Type: Journal
• Year: 2012
• Where: CVPR
• Authors: A. Elhayek, Carsten Stoll, Nils Hasler, Kwang In Kim, Hans-Peter Seidel, Christian Theobalt
• Keywords: Computer Vision, Cvpr 2012, Image Similarity, Similarity Measure, Temporal Detail