A Simultaneous Estimation Method of Camera Pose and Environment Model using Head Mounted Stereo Vision

To realize multipurpose recognition system for various robots, it is necessary to design the recognition system which is independent from robot body. When human equipped the system, we can obtain sensor logs with difficult motion for robots, and apply recognized information from logs to robot navigation. In this paper, we make a head mounted stereo vision sensor system and propose a simultaneous estimation method of camera pose and environment model in real environment. We show some environment models as results.

[1]  Olivier Stasse,et al.  Real-time 3D SLAM for Humanoid Robot considering Pattern Generator Information , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Kimitoshi Yamazaki,et al.  Object shape reconstruction and pose estimation by a camera mounted on a mobile robot , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[3]  Kazuhiko Sumi,et al.  3D Digitization of a Hand-Held Object with a Wearable Vision Sensor , 2004, ECCV Workshop on HCI.

[4]  Hideaki Kuzuoka,et al.  WACL: supporting telecommunications using - wearable active camera with laser pointer , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[5]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[7]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Richard A. Volz,et al.  Estimating 3-D location parameters using dual number quaternions , 1991, CVGIP Image Underst..