Initialization and System Modeling in 3-D Pose Tracking

Initialization and choice of adequate motion models are two important but seldom discussed problems in 3D model-based pose (position and orientation) tracking. In this paper, we propose an automatic initialization approach suitable for textured objects. In addition, we define, study and experimentally evaluate three motion models commonly used in visual servoing and augmented reality

[1]  Wolfgang Ponweiser,et al.  Edge-Projected Integration of Image and Model Cues for Robust Model-Based Object Tracking , 2001, Int. J. Robotics Res..

[2]  Lindsay Kleeman,et al.  Fusion of multimodal visual cues for model-based object tracking , 2003 .

[3]  Greg Welch,et al.  SCAAT: incremental tracking with incomplete information , 1997, SIGGRAPH.

[4]  Vincent Lepetit,et al.  Point matching as a classification problem for fast and robust object pose estimation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[5]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Volker Graefe,et al.  Dynamic monocular machine vision , 1988, Machine Vision and Applications.

[7]  Roberto Cipolla,et al.  Real-Time Visual Tracking of Complex Structures , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Chris Harris,et al.  Tracking with rigid models , 1993 .

[10]  Danica Kragic,et al.  Integration of Model-based and Model-free Cues for Visual Object Tracking in 3D , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[11]  Vincent Lepetit,et al.  Stable real-time 3D tracking using online and offline information , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Hans-Hellmut Nagel,et al.  Model-based object tracking in monocular image sequences of road traffic scenes , 1993, International Journal of Computer 11263on.

[13]  Danica Kragic,et al.  Receptive field cooccurrence histograms for object detection , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Vincent Lepetit,et al.  Point matching as a classification problem for fast and robust object pose estimation , 2004, CVPR 2004.