隨著科技的不斷發展，各種利用機器視覺與影像處理的方式來達到物件追尋的理論也不斷被提出。多數的物件追尋方式利用物體的形狀特徵來做為物件追尋的依據，如此一來需要有追尋物體的形狀特徵，但很多時候我們希望能夠追尋形狀特徵未知，但速度或移動方向明確物體，例如特定的速度、特定的移動方向。因此本文描述一種在時空域中的方法，不受物體形狀特徵的影響，而是利用物體的速度特徵來做為追尋的依據，達到物件追尋的效果。並提出以光流法與時空域中的方法結合，以求整個物件追尋系統更加完善。

As a result of everlasting developments in multimedia technologies, all kinds of objects tracking theory using machine vision or image process methods have been proposed. Most of the methods are based on shape of the object. For this reason, the profile of the tracked object must be known in advance. In many situations, we expect to track the object whose shape is unknown but speed or direction is explicit. For instance, speed or moving direction of the object is known. This thesis presents a spatio-temporal tracking technique, which extracts image information depending on speed of the moving object regardless of its shape. Furthermore, combination of the proposed method in spatio-temporal domain and the optical flow scheme makes the whole tracking system even more robust.

目錄 I
圖索引 IV
表索引 VII
摘要 VIII
ABSTRACT IX
第一章 緒論 1
1.1 動機與目的 1
1.2 文獻回顧 2
1.3 論文架構 7
第二章 物件追尋 8
2.1 空間域的定義與追尋方法 8
2.2 頻域的定義與追尋方法 10
2.3 時空域的定義與追尋方法 14
第三章 三維平面共振濾波器 16
3.1 相關理論 16
3.1.1 影像流的定義 16
3.1.2 傅立葉轉換 17
3.1.3 一階三維系統函數 18
3.1.4 雙線性轉換 18
3.2 平面共振濾波器之設計 19
3.2.1 時空域中的共振平面 19
3.2.2 三維的共振平面系統 21
3.2.3 平面共振疊代濾波器 24
3.2.4 一階三維系統穩定性 27
3.2.5 特定影像流物件強化 29
3.3 自主性物件追尋系統 29
3.3.1 亮度質量中心 30
3.3.2 追尋演算法 32
第四章 光流法與其應用 35
4.1 光流與影像流之定義 35
4.2 光流值的演算 36
4.3 以特徵為基礎的光流法 40
4.4 與平面共振濾波器之結合應用 43
第五章 實驗模擬與分析 47
5.1 實驗參數設定 47
5.2 實驗模擬 49
5.2.1 圓形物件與矩形物件不交錯移動 49
5.2.2 矩形物件與矩形物件不交錯移動 52
5.2.3 矩形物件與矩形物件交錯移動 54
5.2.4 圓形物件與矩形物件曲線移動 57
5.2.5 真實世界影像模擬 61
5.2.6 真實世界影像模擬(導入光流法) 63
5.2.7 矩形物件的劇烈變化移動 65
5.2.8 矩形物件的劇烈變化移動(導入光流法) 67
5.2.9 三維空間頻寬數據測試 69
第六章 結論與未來展望 72
參考文獻 74
附錄一 實驗四影像流值 78
附錄二 平面共振濾波器係數推導 80

[1]R. C. Gonzalez, and R. E. Woods. Digital Image Processing, Perason Prentice Hall, ISBN: 013168728X, 2007.
[2]J. G. Daugman, “Uncertainty relations for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters,” Journal of the Optical Society of America, Vol. 2, pp. 1160-1169, 1985.
[3]S. E. Grigorescu, N. Petkov, and P. Kruizinga, “Comparison of texture features based on Gabor filters,” IEEE Trans. on Image Processing, Vol. 11, No. 10, pp. 1160-1167, 2002.
[4]D. Dunn, W. E. Higgins, and J. Wakeley, “Texture segmentation using 2-D Gabor elementary functions,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 16, No. 2, 1994.
[5]S. Arivazhagan, L. Ganesan, and S. Bama, “Fault segmentation in fabric images using Gabor wavelet transform,” Machine Vision and Application, Vol. 16, No. 6, pp. 356-363, 2006.
[6]A. Bodnarova, M. Bennamoun, and S. Latham, “Optimal Gabor filters for textile flaw detection,” Pattern Recognition, Vol. 35, No. 12, pp. 2973-2991, 2002.
[7]D. M. Tsai, and S. K. Wu, “Automated surface inspection using gabor filters,” International Journal of Advanced Manufacturing Technology, Vol. 16, No. 7, pp. 474-482, 2000.
[8]A. C. Bovik, M. Clark, and W. S. Geisler “Multichannel texture analysis using localized spatial filters,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 12, No. 1, pp. 55-73, 1990.
[9]林明秀、董學志、及宋建中，Gabor小波目標特徵提取和跟蹤方法的研究，光電工程，第31卷，26-29頁，民國93年。
[10]X. H. Duan, P. A. Wang, and D. S. Xia, “Phase differential technique based on estimation of optical flow,” Journal of Data Acquisition and Processing, Vol. 20, No. 3, pp. 249-253, 2005.
[11]Z. Z. Jia, L. W. Dong, B. Dong, and Y. D. Xie, “Comparsion study of Fourier transform,Gabor transform and wavelet transform,” Journal of Anshan University of Science and Technology, Vol. 28, No. 1, pp. 12-17, 2005.
[12]陳筱梅，基於小波轉換的雜訊影像增強研究，國立台灣海洋大學資訊工程學系碩士論文，民國94年。
[13]J. C. Liu, W. L. Hwang, M. S. Chen, J. W. Tsai, and C. H. Lin, “Wavelet based active contour model for object tracking,” IEEE, Image Processing, Vol. 3, pp. 206-209, 2001.
[14]L. T. Bruton, and N. R. Bartley, “Multidimensional network resonance and applications in image processing” in Proc. IEEE Int. Circuits Systems, pp. 388-401, 1983.
[15]L. T. Bruton, and N. R. Bartley, “The enhancement and tracking of moving objects in digital images using adaptive three-dimensional recursive filters,” IEEE Trans. Circuits and System, Vol. 33, No. 6, pp. 604-613, 1986.
[16]李慧婷，以特徵為基礎之光流計算方法，國立中山大學機械工程研究所碩士論文，民國八十八年六月。
[17]楊武智編譯，影像處理與辨認，全華科技圖書股份有限公司，ISBN : 957-21-0788-7，民國八十三年十二月初版。
[18]E. H. Adelson, and J. R. Bergen, “Spatio-temporal energy models for the perception of motion,” Journal of Optical Society of America, Vol. 2, No. 2, pp. 284-299, 1985.
[19]B. Porat, and B. Friedlander, “A frequency domain algorithm for multiframe detection and estimation of dim targets,” Pattern Analysis and Machine Intelligence, IEEE Transactions, Vol. 12, No. 4, pp. 398-401, 1990.
[20]L. T. Bruton, and N. R. Bartley “Three-dimensional image processing using the concept of network resonance,” IEEE Trans. Circuits and System, Vol. 32, No. 7, pp. 664-672, 1985.
[21]P. Agathoklis, and L. T. Bruton, “Practical BIBO-stability of n-dimensional discrete systems,” in Proc. IEEE Int. Symp. on Circuits and Systems (ISCAS '84), pp. 923-926,1983.
[22]B. K. P. Horn, and B. G. Schunck, “Determining optical flow,” Artificial Intelligence, Vol. 17, pp. 185-203, 1981.
[23]E. P. Simoncelli, E. H. Adelson, and D. J. Heeger, “Probability distribution of optical flow,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 310-315, 1991.
[24]B. Lucas, and T. Kanade, “An iterative image registration technique with an application to stereo vision,” in Proc. DARPA Image Understanding Workshop, pp. 121-130, 1981.
[25]C. C. Cheng, and H. T. Li, “Feature-based optical flow computation,” International Journal of Information Technology, Vol. 12, No. 7, 2006.
[26]景雅新，光流技術在移動物體影像追尋上之應用，國立中山大學機械工程研究所碩士論文，民國九十二年。