本論文的主要內容是透過深度感測器對實際場景中的三維物體進行追蹤，並對追蹤過程中更換的物體加以辨識。本論文基本上分成三個階段，第一個階段為離線訓練階段，第二個階段為在線追蹤階段，第三個階段為辨識階段。第一個階段，先分別對要追蹤的物體(長方體、圓柱體以及球體)建立出3D模型，接著分別計算這些3D模型表面的點對特徵，並儲存於一個資料庫中。第二階段，使用深度感測器將場景資訊讀取進來，一樣計算出場景的點對特徵，並且與資料庫中的點對特徵比對，比對完後便可得知場景中實際追蹤物體的位置，並計算出一個初始姿態，有了初始姿態後，表示3D模型已經大略與實際追蹤物體相互疊合，但非完全疊合，所以本文透過疊代最近點演算法(ICP)來計算出更精確的姿態，使模型與實際追蹤物體完全疊合，達到追蹤的效果。第三階段，我們會在執行追蹤的過程中，將實際的追蹤物體做替換，例如將長方體替換成圓柱體，當實際物體被替換時，本方法可透過3D模型與實際追蹤物體的距離來偵測出場景中的追蹤物體已被替換，並且辨識出新的追蹤物體，然後繼續以第二階段的方法對新的追蹤物體進行追蹤。

The main purpose of this paper is 3D object tracking by using RGB-D camera. In addition, we would change our object during the tracking phase and our system can identify the new object. This paper is basically composed of three phases. The first phase is off-line training. The second phase is on-line tracking. The third phase is identification of the new object. In the first phase, we create three 3D models of the tracking objects which are box, cylinder and sphere, and we use a method to calculate the point pair features for each 3D model. Then, we store those point pair feature into the database which would be used later. In the second phase, use the RGB-D sensor to obtain the real world scenery, and calculate the point pair feature of the real world scenery as well as the first phase. After that, we compare the scenery 's point pair features to the database so that we can find out where the 3D model is in the scenery. However, it is just an initial pose for the 3D model, so here we have to use the Iterative Closet Point (ICP) algorithm to obtain a better pose. In the third phase, we would change the tracking object during the tracking phase, and our system can detect the situation from the scenery. Besides, it can identify the new tracking object and keep tracking of it by the method introduced in the second phase.

論文審定書 i
中文摘要 ii
Abstract iii
圖目錄 vii
第一章 緒論 1
1-1 研究動機與目的 1
1-2 論文架構 2
第二章 背景介紹 3
2-1 點對特徵 3
2-2 疊代最近點演算法(Iterative Closest Point) 4
2-3 K-D樹(K-D Tree) 4
2-3-1 最近點搜尋 5
2-3 雜湊函式(Hash Function) 6
2-4 雜湊表(Hash Table) 6
2-5 微軟Kinect感應器 7
2-6 微軟官方軟體開發套件 7
第三章 研究方法 9
3-1 系統架構 9
3-2 建立3D模型 11
3-3 離線儲存模型 11
3-3-1 降取樣 12
3-3-2 全局模型描述(Global Model Description) 12
3-4 計算初始姿態 14
3-4-1 局部座標(Local Coordinates) 15
3-4-2 投票機制(Voting Scheme) 16
3-4-3 群聚姿態 17
3-5 計算精確姿態 19
3-5-1 設定點集合 20
3-5-2 設定結束疊代條件 21
3-5-3 尋找對應點 21
3-5-4 計算平移及旋轉矩陣 22
3-5-5 更新模型姿態 22
3-6 辨識階段 23
第四章 實驗結果 24
4-1 實驗環境 24
4-2 實驗方法 25
4-3 實驗結果 26
4-3-1 追蹤精確度 30
4-3-2 比較不同方法對追蹤精確度的影響 30
第五章 結論與未來展望 33
參考文獻 34

[1] R. Azuma, "A Survey of Augmented Reality", Teleoperators and Virtual Environments, vol. 6, no. 2-3, pp. 355-385, 1997.
[2] J. Smisek, M. Jancosek, and T. Pajdla, "3D with Kinect", IEEE International Conference on Computer Vision Workshops, 2011.
[3] B. Drost, M. Ulrich, N. Navab, and S. Ilic, "Model Globally, Match Locally: Efficient and Robust 3D Object Recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 998-1005, 2010.
[4] B. Drost, S. Ilic, "3D Object and Localization Using Multimodal Point Pair Features", Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission, pp. 9-16, 2012.
[5] P.J. Besl, N.D. McKay, "A Method for Registration of 3-D Shapes", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, 1992.
[6] S. Rusinkiewicz, M. Levoy, "Efficient Variants of the ICP Algorithm", IEEE International Workshop on 3D Digital Imaging and Modeling, pp. 145-152, 2001.
[7] T. Zinsser, J. Schmidt, and H. Niemann, "A Refined ICP Algorithm for Robust 3-D Correspondence Estimation", Proceedings 2003 International Conference on Image Processing, vol. 2, pp. 695-8, 2003.
[8] A. Segal, D. Haehnel, and S. Thrun. "Generalized-ICP", Proceedings of Robotics: Science and Systems, 2009.
[9] J.L. Bentley, "Multidimensional Binary Search Trees Used for Associative Searching", Communications of the ACM, vol. 18, no. 9, pp. 509-517, 1975.
[10] K-d tree, [online] Available: https://en.wikipedia.org/wiki/K-d_tree.
[11] J.H. Friedman, J.L. Bentley, R.A. Finkel, "An Algorithm for Finding Best Matches in Logarithmic Expected Time", ACM Transactions on Mathematical Software, vol. 3, no. 3, pp. 209-226, 1997.
[12] Hash Function, [online] Available: https://en.wikipedia.org/wiki/Hash_function.
[13] Hash Table, [online] Available: https://en.wikipedia.org/wiki/Hash_table.
[14] Z. Zhang, "Microsoft Kinect Sensor and its Effect", IEEE Multimedia, vol.19, no.2, pp.4-10, 2012.
[15] Kinect Developers, "Kinect for Windows SDK 1.8", [online]Avalaible:
https://www.microsoft.com/en-us/download/details.aspx?id=40278
[16] K.S. Arun, T.S. Huang, and S.D. Blostein, "Least-Squares Fitting of Two 3-D Point Sets", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. PAMI-9, no. 5, pp. 698-700, 1978.