3D Velocity Measurement of High-Speed Rotating Sphere Based on the Monocular Vision Servo System

The information processed by monocular vision is a target object that projects from 3D to 2D. So restoring the depth information has a significant influence on the prediction of target trajectory and subsequent control decision. This paper proposes an algorithm based on monocular vision, which can be used to calculate 3D velocity of high-speed rotating sphere, this will be applied to vision recognition of table tennis robot, and play an important role in robots’ motion plan and decision control. The experimental results of the proposed algorithm are verified with little error, which proves the feasibility of the proposed method.

[1]  Liu Sheng-lan.  Monocular measurement in binocular measurement system with instantaneous random illumination , 2010 .

[2]  Ashutosh Saxena,et al.  Learning Depth from Single Monocular Images , 2005, NIPS.

[3]  Fumio Miyazaki,et al.  A learning approach to robotic table tennis , 2005, IEEE Transactions on Robotics.

[4]  Kenji Terada,et al.  A method of distance measurement by using monocular camera , 1997, Proceedings of the 36th SICE Annual Conference. International Session Papers.

[5]  Chunfang Liu,et al.  A registration algorithm for on-line measuring the rotational velocity of a table tennis ball , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[6]  Qiang Huang,et al.  Dynamic model based ball trajectory prediction for a robot ping-pong player , 2010, 2010 IEEE International Conference on Robotics and Biomimetics.

[7]  Lei Sun,et al.  Ball's flight trajectory prediction for table-tennis game by humanoid robot , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[8]  Chunfang Liu,et al.  Robotic table tennis based on physical models of aerodynamics and rebounds , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[9]  De Xu,et al.  Trajectory prediction of spinning ball for ping-pong player robot , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.