本文之目標旨在實作運動物件追蹤之方法。透過物件狀態估測器之實作，針對簡單幾何外形之移動物件進行狀態估測。利用工業用CCD相機，針對特定區域進行影像取樣分析，獲取關於物件之狀態資訊，
首先，本文將針對關於機械視覺、物件輪廓追蹤與辨識以及視覺系統於自動化應用之相關研究進行文獻回顧。相關之基本影像處理方法、影像校正原理則隨後闡述，接著並說明物件狀態估測法之整體架構與流程。在系統配置中，則主要說明完整之系統方塊圖，CCD相機可視範圍估算以及影像座標系與機械座標系間座標之轉換關係。最後則針對狀態估測結果與相關之影響因素進行實驗以及數據分析，以驗證本狀態估測流程之準確性。

The procedure of object motion states estimation is developed in the paper. For moving objects with simple geometry, the information about motion states can be obtained via the implementation of object state estimator module. Using industrial CCD camera, the sampled images of the specified viewing area in the scene are analysed and the information about objects is extracted.
First, paper review on machine vision, object contour tracking and recognition, related study about machine vision application in industrial automation is shown. Basic image processing method, calibration, the framework of object state estimation and procedure are explained later. In the topic of system configuration, the block diagram of whole system, the estimation of field of view of CCD and the transformation between image coordinate system and machine coordinate system are shown. Finally, the accuracy and viability of the module are verified experimentally.

參考文獻
[1] “影像圖形辨識法則與相關產品市場動態”, Image Processing Magazine, 1999.
[2] N. Ayache and O.D. Faugeras, “HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects”, IEEE Trans. on Pattern Analysis and Machine Intelligence, 1986.
[3] S. Suzuki and K. Abe, “Topological Structural Analysis of Digitized Binary Images by Border Following”, Computer Vision, Graphics, and Image Processing 30, 32-46, 1985.
[4] H. Dang, Y. Hong, X. Fang and F. Qiang, “Initial Contour Automatic Selection of Geometric Active Contour Model”, Intelligent Computation Technology and Automation, 2009.
[5] J. Xu, D. Bi and Z. Wei, “A Novel Robust Contour Tracking Algorithm”, ISME International Conference, 2010.
[6] J. Rao, J. Lin, S. Xu and S. Lin, “A New Intelligent Contour Tracking Algorithm in Binary Image”, ICDH 4th International Conference, 2012.
[7] W. Li, X. Zhang and W. Hu, “Contour Tracking with Abrupt Motion”, Image Processing(ICP), 16th IEEE International Conference, 2009.
[8] M. K. Hu, “Visual Pattern Recognition by Moment Invariants”, Information Theory, IRE Transactions, 1962.
[9] Q. Chen, E. Petriu and X. Yang, “A Comparative Study of Fourier Descriptor and Hu’s Seven Moment Invariants for Image Recognition”, Electrical and Computer Engineering, Canadian Conference, 2004.
[10] I. Konukseven and B. Kaftanoglu, “Moving Part Recognition and Automatic Pick and Place Using Industrial Robot”, Intelligent Robots and Systems, Proceedings of the 1997 IEEE/RSJ International Conference, 1997.
[11] T. Kotthauser and G. Mauer, “Vision-Based Autonomous Robot Control for Pick and Place Operation”, Advanced Intelligent Mechatronics, AIM IEEE/ASME International Conference, 2009.
[12] S. Lee, J. Kim, M. Lee, K. Yoo, L. G. Barajas and R. Menassa, “3D Visual Perception System for Bin Picking in Automotive Sub-Assembly Automation”, Automation Science and Engineering(CASE), IEEE International Conference, 2012.
[13] O. Skotheim, M. Lind, P. Ystgaard and S. A. Fjerdingen, “A Flexible 3D Object Localization System for Industrial Part Handling”, Intelligent Robots and Sytems(IROS), IEEE/RSJ International Conference, 2012.
[14] M. Sonka, V. Hlavac and R. Boyle,“Image Processing, Analysis, and Machine Vision”, 2nd edition.
[15] E. Rosten and T. Drummond,“Machine Learning for High-Speed Corner Detection”, 9th European Conference on Computer Vision, Graz, Austria, May 2006.