Binocular Visual Tracking : Integration of Perception and Control

This paper presents an active binocular tracking system including both the perceptual and control points of view. In the perceptual part, a signiicant aspect is that we make use of a space variant sensor geometry implementing a focus of attention in the center of the visual eld, which favours the tracking process. Simple and fast low-level vision algorithms are employed, allowing real-time (16.7 Hz) and reliable performance. The control part is developed according to the visual servoing framework, including the kinematics and dynamics of our system. We show that under certain assumptions the kinematic relations in our system become very simple and decoupled as well as system dynamics can be expressed in the image feature space. These facts allow the design of simple dynamic controllers for each degree of freedom directly from the image feature space properties. The overall system is implemented in the Medusa stereo head without any speciic processing hardware. Results of tracking experiments are presented and illustrate the performance of the system with diierent control strategies and with objects of diierent shapes and motions.

[1]  R. Carpenter,et al.  Movements of the Eyes , 1978 .

[2]  Gene F. Franklin,et al.  Digital control of dynamic systems , 1980 .

[3]  Francis L. Merat,et al.  Introduction to robotics: Mechanics and control , 1987, IEEE J. Robotics Autom..

[4]  Yehezkel Yeshurun,et al.  Cepstral Filtering on a Columnar Image Architecture: A Fast Algorithm for Binocular Stereo Segmentation , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  R. L. Andersson Dynamic sensing in a ping-pong playing robot , 1989, IEEE Trans. Robotics Autom..

[6]  Patrick Rives,et al.  Positioning of a robot with respect to an object, tracking it and estimating its velocity by visual servoing , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[7]  Pascal Fua,et al.  Quantitative and Qualitative Comparison of Some Area and Feature-based Stereo Algorithms , 1992 .

[8]  Patrick Rives,et al.  A new approach to visual servoing in robotics , 1992, IEEE Trans. Robotics Autom..

[9]  Takeo Kanade,et al.  Visual tracking of a moving target by a camera mounted on a robot: a combination of control and vision , 1993, IEEE Trans. Robotics Autom..

[10]  Nikolaos Papanikolopoulos,et al.  Six degree-of-freedom hand/eye visual tracking with uncertain parameters , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[11]  Gregory D. Hager,et al.  Robot hand-eye coordination based on stereo vision , 1995 .

[12]  Giulio Sandini,et al.  Space-variant vision for an active camera mount , 1995, Defense, Security, and Sensing.

[13]  Peter I. Corke,et al.  A tutorial on visual servo control , 1996, IEEE Trans. Robotics Autom..

[14]  Peter I. Corke,et al.  Dynamic effects in visual closed-loop systems , 1996, IEEE Trans. Robotics Autom..

[15]  Peter Corke,et al.  Visual Control of Robots: High-Performance Visual Servoing , 1996 .

[16]  Alexandre Bernardino,et al.  Vergence control for robotic heads using log-polar images , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[17]  A. Bernardino Correlation Based Vergence Control Using Log-polar Images ? , 1996 .