臺灣博碩士論文加值系統

本論文的目的在於利用固定背景下的即時影像，建立一個與亮度無關的移動物影像追蹤系統。首先分成移動物件的偵測與物件追蹤兩部分，在移動偵測方面，運用影像處理的技術建立目前影像環境的背景影像，利用影像處理動差（Moment）的特性及統計檢定的法則處理目前影像與背景影像的差異，消除雜訊，及門檻值的求取，將移動物件與背景分離；在物件追蹤方面，利用卡門濾波器（Kalman Filter）的特性追蹤及預測移動物件。本論文所提出方法之特色：是在影像經過任何前置處理之前先進行移動偵測的好處在於可減少所處理原始影像資料的數量；再利用簡化的卡門濾波器更有效率的追蹤及預測移動物件。實驗結果將顯示所提方法之可行性。

The purpose of this thesis is using the real-time image of fixed background to build up a motion object tracking system which is not related with the variation of illumination. This system consists of two phases, i.e., the phase of motion object detection and the phase of tracking. In the first phase, the motion object is extracted by noticing the differences between the current and the background images. The techniques involved include the calculation of the moment and the statistical hypothesis testing. In the second phase, the method of Kalman Filter is adopted to track and predict the positions of moving object. In addition, the process of the Kalman Filter is simplified so as to greatly reduce the processing time and satisfy the requirement of real-time process. Finally, the experimental results reveals the feasibility of the proposed method.

目 錄
書名頁 1
摘 要 2
ABSTRACT 3
目 錄 4
圖目錄 6
表目錄 8
第一章 前言 9
1.1 研究動機 9
1.2 相關研究 9
1.3 章節架構 12
第二章 基本觀念介紹 13
2.1 動差之基本觀念 13
2.2 卡門濾波器之基本觀念 14
第三章 擬提方法 31
3.1 基本作法與流程介紹 31
3.1 移動偵測方法－SCSM法 32
3.1.1 SCSM法的前身CSM法 32
3.1.2 SCSM法 37
3.2 物件追蹤方法－簡化的卡門濾波器（Simplify Kalman Filter） 40
第四章 實驗結果 47
4.1 實驗設備 47
4.2 實驗結果 47
第五章 結論與未來研究方向 62
參考文獻 64

參考文獻
[1] M. Sonka, V. Hlavac, and R. Boyle, Image Processing, Analysis, and Machine Vision, Books / PWS Publishing, pp. 232-234, 1999.
[2] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Books / Prentice Hall, pp. 672-675, 2002.
[3] G. Welch and G. Bishop, “An introduction to the kalman filter,” UNC-Chapel Hill, NC 27599-3175, pp. 1-16, 2001.
[4] Larry J. Levy, “The kalman filter : navigation’s integration workhorse,” GPS World, Vol. 8, pp. 65-71, 1997.
[5] C. K. Chui and G. Chen, Kalman Filtering with Real-Time Applications, Springer-Verlag, Berlin, 1987.
[6] D. Han, C. Y. Shih, S. J. Choi, and J. S. Park, “A motion adaptive 3-D de-interlacing algorithm based on the brightness profile pattern difference,” IEEE Transactions on Consumer Electronics, Vol. 45, No. 3, pp. 690-696, 1999.
[7] 楊武智 編譯,影像處理與辨認,全華科技圖書股份有限公司, pp. 217-222, 1999.
[8] 游世豪,與陳永盛博士 “交通監控系統之研究, ”元智大學電機工程研究所碩士論文, 2002.
[9] O. Masoud and N. P. Papanikolopoulos, “A robust real-time multi-level model-based pedestrian tracking system,” Proc. ITS America Seventh Annual Meeting, Washington, DC, pp. 1-22, June 1997.
[10] S. N. Jayaramamurthy and R. Jain, “An approach to the segmentation of textured dynamic scenes,” Computer Vision, Graphics and Image Processing, Vol. 21, pp. 239-261, 1983.
[11] C. E. Smith, S. A. Brandt, C. A. Richards, and N. P. Papanikolopoulos, “Visual tracking for intelligent vehicle-highway systems,” IEEE Transactions on Vehicular Technology, Vol. 45, No. 4, pp. 744-759, 1996.
[12] Y. Z. Hsu, H. H. Nagel, and G. Refers, “New likelihood test methods for change detection in image sequence,” Computer Vision, Graphics and Image Processing, Vol. 26, pp. 73-106, 1984.
[13] K. Skifstad and R. Jain, “Illumination independent change detection from real world image sequences,” Computer Vision, Graphics and Image Processing, Vol. 46, pp. 387-399, 1989.
[14] S. L. Liu, C. W. Fu, and S. Chang, “Statistical change detection with moment under time-varying illumination,” IEEE Transactions on Image Processing, Vol. 7, No. 9, pp. 1258-1268, 1998.
[15] L. H. Chen and S. Chang, “A video tracking system with adaptive predictors,” Pattern Recognition, Vol. 25, pp. 1171-1180, 1992.
[16] 鍾國亮 著,影像處理與電腦視覺,東華書局,pp. 296-300, 2002.
[17] G. Rigoll, B. Winterstein, and S. Müller, “Robust person tracking in real scenarios with non-stationary background using a statistical computer vision approach,” IEEE International Workshop on Visual Surveillance in conjunction with CVPR-99, Fort Collins, USA, pp. 41-47, June 1999.
[18] A. M. Baumberg and D. C. Hogg, “An efficient method for contour tracking using active shape models,” Proc. IEEE Workshop on Motion of Non-Rigid and Articulated Objects, pp. 194-199, 1994.
[19] O. Masoud and N. P. Papanikolopoulos, “The use of computer vision in monitoring weaving sections,” IEEE Transactions on Intelligent Transportation Systems, Vol. 2, No. 1, pp. 18-25, 2001.
[20] O. Masoud, N. P. Papanikolopoulos, and E. Kwon, “Vision-based monitoring of weaving section,” Proc. of IEEE conference on Intelligent Transportation Systems, pp. 770-775, October 1999.
[21] D. Koller, N. Heinze, and H. H. Nagel, “Algorithmic characterization of vehicle trajectories from image sequences by motion verbs,” IEEE Computer Society Conference, pp. 90-95, June 1991.
[22] D.M. Gavrila and J. Giebel, “Shape-based pedestrian detection and tracking,” IEEE 2002 Intelligent Vehicle Symposium, Vol. 1, pp. 8-14, June 2002.
[23] F. Dellaert and C. Thorpe, “Robust car tracking using kalman filtering and bayesian templates,” SPIE Conference on Intelligent Transportation Systems, Pittsburgh, PA, 1997.
[24] A. Rosenfeld and A. C. Kak, Digital Picture Processing. Academic, New York, 1982.
[25] T. Aach, A. Kaup, and R. Mester, “Statistical model-based change detection in moving video,” Signal Processing, Vol. 31, pp. 165-180, Mar. 1993.
[26] R. E. Walpole and R. H. Myers, Probability and Statistics for Engineers and Scientists, 5th ed., Macmillan, New York, 1993.