Random-forest-based initializer for solving inverse problem in 3D motion tracking systems
暂无分享,去创建一个
Many motion tracking systems require solving inverse problem to compute the tracking result from original sensor measurements. For real-time motion tracking, such typical solutions as the Gauss-Newton method for solving their inverse problems need an initial value to optimize the cost function through iterations. A powerful initializer is crucial to generate a proper initial value for every time instance and, for achieving continuous accurate tracking without errors and rapid tracking recovery even when it is temporally interrupted. An improper initial value easily causes optimization divergence, and cannot always lead to reasonable solutions. Therefore, we propose a new initializer based on random-forest to obtain proper initial values for efficient real-time inverse problem computation. Our method trains a random-forest model with varied massive inputs and corresponding outputs and uses it as an initializer for runtime optimization. As an instance, we apply our initializer to IM3D[1], which is a real-time magnetic 3D motion tracking system with multiple tiny, identifiable, wireless, occlusion-free passive markers (LC coils).
[1] Yoshifumi Kitamura,et al. IM3D: magnetic motion tracking system for dexterous 3D interactions , 2014, SIGGRAPH '14.
[2] Yasuo Okazaki,et al. Wireless magnetic motion capture system using multiple LC resonant magnetic markers with high accuracy , 2008 .
[3] Weida Tong,et al. Decision Forest: Combining the Predictions of Multiple Independent Decision Tree Models , 2003, J. Chem. Inf. Comput. Sci..