[1] Wang Huaming, Luo Xiang, Zhu Jianying,. 3-D visual tracking based on CMAC neuralnetwork and Kalman filter [J]. Journal of Southeast University (English Edition), 2003, 19 (1): 58-63. [doi:10.3969/j.issn.1003-7985.2003.01.014]

Copy

3-D visual tracking based on CMAC neuralnetwork and Kalman filter()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

19

Issue:

2003 1

Page:

58-63

Research Field:

Automation

Publishing date:

2003-03-30

Info

Title:

3-D visual tracking based on CMAC neuralnetwork and Kalman filter

Author(s):

Wang Huaming¹;  Luo Xiang²;  Zhu Jianying¹

¹College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
²Department of Mechanical Engineering, Southeast University, Nanjing 210096, China

Keywords:

visual tracking;  CMAC;  neural network;  Kalman filter

PACS:

TP24

DOI:

10.3969/j.issn.1003-7985.2003.01.014

Abstract:

In this paper, the Kalman filter is used to predict image feature position around which an image-processing window is then established to diminish feature-searching area and to heighten the image-processing speed. According to the fundamentals of image-based visual servoing(IBVS), the cerebellar model articulation controller(CMAC)neural network is inserted into the visual servo control loop to implement the nonlinear mapping from the error signal in the image space to the control signal in the input space instead of the iterative adjustment and complicated inverse solution of the image Jacobian. Simulation results show that the feature point can be predicted efficiently using the Kalman filter and on-line supervised learning can be realized using CMAC neural network; end-effector can track the target object very well.

References:

[1] Shirai Y, Inoue H. Guiding a robot by visual feedback in assembling tasks [J]. Pattern Recognition, 1973, 5(2):99-108.
[2] Hill J, Park W T. Real time control of a robot with a mobile camera [A]. In: Proc of the 9th International Symposium on Industrial Robots(ISIR) [C]. Washington DC, 1979.233-246.
[3] Kallio Pasi, Zhou Quan, Koivo Heikki N. Control issues in micromanipulation [A]. In: International Symposium on Micromechatronics and Human Science[C]. 1998.135-141.
[4] Nelson B J, Papanikolopoulos N P, Khosla P K. Visual servoing for robotic assembly[A]. In: Hashimoto, ed. Visual Servoing-Real-Time Control of Robot Manipulator Based on Visual Sensory Feedback[C]. River Edge, NJ: World Scientific, 1993.139-164.
[5] Corke P I, Hutchinson S A. Real-time vision, tracking and control [A]. In: Proceedings of the 2000 IEEE International Conference on Robotics and Automation[C]. San Francisco, CA, 2000.622-629.
[6] Hutchinson S A, Hager G, Corke P I. A tutorial on visual servo control [J]. IEEE Trans on Robotics and Automation, 1996, 12(5):651-670.
[7] Vikramaditya Barmeshwar, Nelson Bradley J. Visually guided microassembly using optical microscopes and active vision techniques [A]. In: IEEE International Conf on Robotics and Automation[C]. Albuquerque, New Mexico, 1997.3172-3177.
[8] Albus J S. A new approach to manipulator control: The cerebellar model articulation controller(CMAC)[J]. Trans of the ASME: Journal of Dynamic Systems, Measurement and Control, 1975, 97(3):220-227.
[9] Miller W T, Glanz F H, Kraft L G. Application of a general learning algorithm to the control of robotic manipulators [J]. International Journal of Robotics Research, 1987, 6(2): 84-98.
[10] Cetinkunt S, Donmez A. CMAC learning controller for servo control of high precision machine tools [A]. In: Proc American Control Conf[C]. San Francisco, CA, 1993.1976-1980.
[11] Ku Sang Soon, Pinsopon Unnat, Cetinkunt Sabri, et al. Design, fabrication, and real-time neural network control of a three-degree-of-freedom nanopositioner [J]. IEEE/ASME Transactions on Mechatronics, 2000, 5(3):273-280.
[12] Kara R, Wira P, Kihl H. Hierarchical neural controller and adaptive Kalman filter for visual robot tracking tasks[R]. University of Mulhouse, France: Technical Report EEA-TROP-TR-00-01, 2000.

Memo

Memo:

Biographies: Wang Huaming(1973—), male, graduate; Zhu Jianying
(corresponding author), male, professor, zjyao@nuaa.edu.cn.

Common functions