本研究以追蹤車牌與辨識為例，建立一個基於影像伺服控制
之移動物動態追蹤與辨識的系統。此系統在相機與鏡頭於追蹤移
動目標物的同時能放大影像並自動聚焦，擷取清晰影像後進行車
牌字元辨識。影像偵測方法上，我們利用樣版比對持續偵測目標
物在影像中的位置，並藉由動態輪廓模型更新因鏡頭放大而變形
的目標物樣版。另外，為使影像清晰，本系統建立一以影像處理
為基礎的自動聚焦功能。在控制方法上，利用卡曼濾波器預測下
一刻目標物的位置，以補償影像回授造成的追蹤延遲，使整體追
蹤時的位置誤差降低。且藉由卡曼濾波器參數的選擇，確保追蹤
的速度誤差符合能擷取清晰車牌字元的攝像標準。整體程序包含
影像處理、鏡頭焦距與焦段的移動、相機的位置控制，可在相機
中斷(亦即20幀/秒)內完成。實驗結果顯示，運用本論文建議之方
法可提升追蹤移動車牌的性能，並準確地辨識此車牌字元。

In this study, a visual servo control system for dynamic pursuit and recogni-
tion for a moving target is established and verified with a car-license-plate exam-
ple. During the entire process, the image of a moving car-license-plate is tracked,
zoomed in, auto-focused, and then captured for recognition. For image process-
ing, template matching method is utilized to detect the position of the moving
car-license- plate, and active contour model is used to update the enlarged tar-
get template as the lens starts zooming in. Besides, an auto focusing function
based on image processing is established to keep images sharp. As for control
algorithms, Kalman filter is used to predict the target position for compensating
for time-delay caused by image processing and reducing tracking errors. In order
to guarantee tracking velocity errors satisfy the criterion for capturing a sharp
image, suitable parameters of Kalman filter are chosen based on simulation. It is
noted that, the overall process consisting of image processing, zooming in, focusing
and position control can be done in 0.05 seconds (i.e., 20 frames/s). Experimental
result shows that, with proposed methods, tracking performance can be improved
and characters on the car license plate can be recognized.

[1] P. Shirkey R. Kelly and M. W. Spong. Fixed-camera visual servo control for
planar robots. In Proceedings of the 1996 IEEE Intemational Conference on
Rcbotics and Automation, pages 2643–2649. IEEE, 1996.
[2] J.S Farrokh and W. J. Wilson. Automatic grasp planning for visual-servo
controlled robotic manipulators. IEEE Transactions on System, Man, and
Cybernetics, 28(5):557–573, 1998.
[3] K. Benameurz and P. R. Belangert. Grasping of a moving object with a
robotic hand-eye system. In Proceedings of the 1998 IEEE/RSJ Intl. Confer-
ence on Intelligent Robots and Systems, pages 304–310. IEEE, 1998.
[4] G. Chesi and K. Hashimoto. Visual Servoing via Advanced Numerical Meth-
ods. Springer, 2010.
[5] D. M. Dawson J. Chen, W. E. Dixon and M. McIntyre. Homography-based
visual servo tracking control of a wheeled mobile robot. IEEE Transactions
on Robotics, 22(2):406–415, 2006.
[6] Z. Ceren and E. Altug. Vision-based servo control of a quadrotor air vehicle.
IEEE International Symposium on Computational Intelligence in Robotics
and Automation, pages 84–89, 2009.
[7] M. A. Turk and A. P. Pentland. Face recognition using eigenfaces. Computer
Vision and Pattern Recognition, pages 586–591, 1991.
[8] M.A Qatran. Template matching method for recognition musnad characters
based on correlation analysis. ACIT’2011 Proceedings, 2011.
[9] P.M. Sharkey and D.W. Murray. Delay versus performance of visually guided
systems. In IEE Proceedings-Control Theory Application, pages 436–447,
1996.
[10] C.K. Wang. Design and implementation of a multi-purpose real-time vi-
sual tracking system based on modified adaptive background substration and
multi-cue template matching. Master’s thesis, National Cheng Kung Univer-
sity, 2004.
103
[11] P. Anandan. Measuring visual motion from image sequences. University of
Massachusetts Amherst, 1987.
[12] L.G Chen H.M Jong and T.D Chiueh. Parallel architectures for 3-step hier-
archical search block-matching algorithm. IEEE Transctions on Circuits and
System for Video Technology, 4(4):407–416, 1994.
[13] F. Leymarie and M.D. Levine. Tracking deformable objects in the plane
using an active contour model. IEEE Transactions on Pattern Analysis and
Machine Intelligence, 15(6):617–634, 1993.
[14] K.M. Lam and H.Yan. Fast greedy algorithm for active contours. Electronics
Letters, 30(1):21–23, 1994.
[15] Y.C Chien. Stochastic resonance in visual manipulation of micro particles.
Master’s thesis, National Cheng Kung University, 2013.
[16] H. Araujo J. P. Barreto, J. Batista. Solution for visual control of motion:
Active tracking applications. In Proceedings of the 8th IEEE Mediterranean
Conference on Control and Automation, 2000.
[17] G.V. McMurray J.A. Piepmeier and H. Lipkin. Tracking a moving target with
model independent visual servoing: a predictive estimation approach. In Pro-
ceedings. 1998 IEEE International Conference on Robotics and Automation,
pages 2652–2657. IEEE, 1998.
[18] J.L Lai. A study on visual detection and tracking of moving targets. Master’s
thesis, National Cheng Kung University, 2013.
[19] E. Brookner. Tracking and Kalman Filtering Made Easy. New York:John
Wiley and Sons, 1998.
[20] T.P. Ojala and D.M. Harwood. Performance evaluation of texture measures
with classification based on kullback discrimination of distributions. In Pro-
ceedings of the 12th IAPR International Conference on Pattern Recognition,
volume 1, pages 582–585, 1994.
[21] P.Y Chen. A robust visual servo system for tracking an arbitrary-shaped
object by a new active contour method. Master’s thesis, National Taiwan
University, 2003.
[22] Jayasooriah T.T.E. Yea, S.H. Ong and R. Sinniah. Autofocusing for tissue
microscopy. Image and Vision Computing, 11:629–639, 1993.
[23] R.C. Gonzalez and R.E. Woods. Digital Image Processing. Upper Saddle
River, 2008.
104
[24] D. Terzopoulos M. Kass, A. Witkin. Snakes: Active contour models. Inter-
national Journal of Computer Vision, 1:321–331, 1987.
[25] D.J.Williams and M. Shah. A fast algorithm for active contours and curvature
estimation. CVGIP:Image Understanding, 55:14–26, 1992.
[26] Y.K. Liao. Study on characteristic recognition in fly vision for automatic
inspection systems. Master’s thesis, National Cheng Kung University, 2014.
[27] W. T. Vetterling W. H. Press, S. A. Teukolsky and B. P. Flannery. Numer-
ical recipes in FORTRAN 77 : the art of scientific computing. Cambridge
University Press, 1992.
[28] N. Otsu. A threshold selection method from gray-level histograms. IEEE
Trans. Sys., Man., 9(1):62–66, 1979.
[29] X. Huadong and L. Dongchu. The study of license plate character segmen-
tation algorithm based on vetical projection. IEEE Computer Society, pages
4583–4586. International Conference on Consumer Electronics, 2011.
[30] A. Jangwanitlert S. Kaitwanidvilai and A. Saenthon. Smart “on the fly vision”
for smart manufacturing inspection system. Proceedings of the IASTED Asian
Conference on Power and Energy Systems, AsiaPES, pages 232–235. Acta
Press, 2012.
[31] M.A. Qatran. Template matching method for recognition musnad characters
based on correlation analysis. ACIT’2011 Proceedings, 2011.
[32] J. Xie. Optical character recognition based on least square support vector
machine. 3rd International Symposium on Intelligent Information Technology
Application, 1:626–629, 2009.
[33] K. Fukushima. Character recognition with neural networks. Neurocomputing,
4(5):221–233, 1992.
[34] J. Y. Stein. Digital Signal Processing: A Computer Science Perspective. John
Wiley and Sons, USA, 2000.
[35] X.W. Lin. Model-fusion-based precision motion control of linear motors. Mas-
ter’s thesis, National Cheng Kung University, 2013.
[36] Y.J. Li. Precision motion control of linear motor with nonlinear friction
phenomena compensation. Master’s thesis, National Cheng Kung University,
2010.
105
[37] K. Astrom and T. Hagglund. PID Controller: Theory, Design and Tuning.
Instrument Society of America, USA, 1995.
[38] U.A. Bakshi and V. Bakshi. Modern Control Theory. Technical Publications,
2009.
[39] S.C. Schneider R.H. Brown and M.G. Mulligan. Analysis of algorithms for ve-
locity estimation from discrete position versus time data. IEEE Transactions
on Industrial Electronics, 39(1):11–19, 1992.
[40] G. Welch and G. Bishop. An introduction to the kalman filter, 1995.
[41] R. G. Brown and P. Y.C. Hwang. Introduction to Random Signals and Applied
Kalman Filtering: with Matlab Exercises and Solutions. JohnWiley and Sons,
1997.
[42] P. Zarchan and H. Musoff. Fundamentals of Kalman Filtering: A Practical
Approach. American Institute of Aeronautics and Astronautics, 2009.
[43] B. P. Gibbs. Advanced Kalman Filtering, Least-Squares and Modeling. John
Wiley and Sons, 2011.