Camera-based 3D Object Tracking and Following Mobile Robot

Camera-based systems are frequently used to track moving objects which are in the field of their view. This paper describes design and development of a camera-based tracking robot that can constantly track moving object without necessity of calibrating camera in real world units then control the two-wheeled moving platform to follow the object. The camera serves as a feedback sensor to guide robot constantly towards the object. The complexity of the system and processing time is less due to the unnecessary camera unit conversions and calibrations. The robot system consists of two subsystems: vision and motion. The vision subsystem consists of a two-motor pan-tilt camera driving mechanism with embedded potentiometer sensor, PCI image acquisition board, and PWM-based DC-motor driver board. The motion subsystem consists of two-wheel and two-castor platform driven by two DC servomotors with amplifiers. The vision subsystem identifies and locates the object in 3D scene by means of image processing techniques and motion control algorithms direct the camera towards the object. Camera motion is then detected by the potentiometer which generates a signal to drive the wheels of the platform. The objective of the vision control is to make sure that the moving object is always at the center of the camera image plane. The system imitates eye tracking ability of a human when he always tends to focus on moving object within the range of its view before any action is taken

[1]  S. Shankar Sastry,et al.  Vision guided navigation for a nonholonomic mobile robot , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[2]  Warren E. Dixon,et al.  Adaptive tracking control of a wheeled mobile robot via an uncalibrated camera system , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[3]  Robert I. Damper,et al.  Evidence-based object tracking via global energy maximization , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[4]  Xiao-Jing Shen,et al.  A simple adaptive control for visual servoing , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[5]  J. Denzler,et al.  Active motion detection and object tracking , 1994, Proceedings of 1st International Conference on Image Processing.

[6]  Christian Balkenius,et al.  Visual tracking and target selection for mobile robots , 1996, Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96).

[7]  Martin Jägersand,et al.  Visual tracking using active appearance models , 2004, First Canadian Conference on Computer and Robot Vision, 2004. Proceedings..

[8]  Martin Jägersand,et al.  Approximating the visuomotor function for visual servoing , 2004, First Canadian Conference on Computer and Robot Vision, 2004. Proceedings..

[9]  Robert I. Damper,et al.  Evidence-based object tracking via global energy maximization , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[10]  Joaquin Sitte,et al.  Real-time motion tracker for a robotic vision system , 2004, First Canadian Conference on Computer and Robot Vision, 2004. Proceedings..