Model-based Motion Capture for Crash Test Video Analysis
Juergen Gall , Bodo Rosenhahn, Stefan Gehrig, and Hans-Peter Seidel
Abstract
In this work, we propose a model-based approach for estimating the 3D position and orientation of a dummy's head for crash test video analysis. Instead of relying on photogrammetric markers which provide only sparse 3D measurements, features present in the texture of the object's surface are used for tracking. In order to handle also small and partially occluded objects, the concepts of region-based and patch-based matching are combined for pose estimation. For a qualitative and quantitative evaluation, the proposed method is applied to two multi-view crash test videos captured by high-speed cameras.
Images/Videos
Video ~10MB (AVI)
Publications
Gall J., Rosenhahn B., Gehrig S., and Seidel H.-P., Model-based Motion Capture for Crash Test Video Analysis (PDF ), 30th Annual Symposium of the German Association for Pattern Recognition (DAGM'08), Springer, LNCS 5096, 92-101, 2008. © Springer-Verlag
Gehrig S., Badino H., and Gall J., Accurate and Model-Free Pose Estimation of Crash Test Dummies Human Motion - Understanding, Modeling, Capture and Animation, Klette R., Metaxas D., and Rosenhahn B. (Eds.), Computational Imaging and Vision, Springer, Vol 36, 453-473, 2008. © Springer-Verlag