臺灣博碩士論文加值系統

隨著科技日新月異，無人控制武器系統成為各國未來發展的重要國防趨勢，目的在於無需有人員操控之下，藉由視覺化技術達到全時自動化監控、辨識或追蹤目標物，但傳統的監控系統大部分是以固定式攝影機為主，對於攝影機隨著載具而有不規則移動的情形下並不適用。
在本論文中，強調可以在攝影機於未知的運動模式下進行偵測，主要方法是利用邊緣梯度作為比對特徵，透過積分影像的方法，除了大幅地提升本演算法的運算速度外，也可快速建立影像平面上的區塊梯度向量值，並經由區塊梯度向量匹配後，便可得到區域運動向量，再藉由這些資訊統計出全域運動向量、角度與強度直方圖，進而獲得攝影機與移動物體相對的運動關係，如果偵測出有移動物體的話，則選取其區域範圍並進行追蹤的動作。由實驗結果可驗證，本論文所提出的梯度向量資訊之影像追蹤與辨識技術是有效的。

As technology advances, the development of unmanned control weapon system will be an important trend to the national defense of every country for in the future. To achieve the full-time automated monitoring, identification or tracking targets through the visual techniques, no one needs to control the system of unmanned control weapons. However, most of the traditional monitoring systems are mainly based on the fixed cameras, and they are not suitable for the condition that the cameras move irregularly with the vehicles.
In this thesis, we emphasize that it is possible to detect the object at unknown movable mode of the cameras. The main method is to use the edge gradient as the comparable features. Then through the method of the Integral Image, the speed of our algorithm becomes very quickly, and we also can create the values of the block gradient vector on the plane of images rapidly. The local motion vectors can be derived from block-matching via the gradient vectors, and then we can count them to get the global motion vectors, the histograms of angle and magnitude separately. Furthermore, the relative movement between the camera and the moving object can be calculated by the global motion vectors. If the moving object is detected, its region is selected and tracked. The experimental results demonstrate that it is effective for the technology of image tracking and recognition based on the gradient vector information in this thesis.

誌謝 ii
中文摘要 iii
ABSTRACT iv
目錄 v
表目錄 viii
圖目錄 ix
1. 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 4
1.3 論文架構 4
2. 文獻探討 5
2.1 偵測移動物體的區域範圍 7
2.1.1 連續影像相減法(Temporal Differencing) 7
2.1.2 背景相減法(Background Subtraction) 9
2.1.3 光流法(Optical Flow) 11
2.2 追蹤移動物體方式 13
2.2.1 區域為基礎之追蹤法(Region-Based Tracking) 13
2.2.2 主動輪廓為基礎之追蹤法(Active-Contour-Based Tracking) 14
2.2.3 特徵為基礎之追蹤法(Feature-Based Tracking) 16
2.2.4 模型追蹤法(Model-Based Tracking) 17
2.3 方向梯度直方圖(HOG) 19
3. 研究方法 21
3.1 影像前處理 23
3.1.1 去交錯處理(Deinterlace) 24
3.1.2 彩色對灰階的影像轉換 25
3.1.3 降解析度處理 25
3.2 區塊梯度向量積分影像 26
3.2.1 邊緣偵測 28
3.2.2 計算梯度積分影像(Integral Image) 33
3.2.3 快速區塊梯度向量值之建立 36
3.3 計算運動向量與其直方圖 37
3.3.1 計算區塊運動向量(Motion Vector) 39
3.3.2 統計運動向量與其直方圖 43
3.4 選取追蹤目標物的區域範圍 47
3.4.1 攝影機與物體相對運動關係 47
3.4.2 閉合處理 51
3.4.3 選取物體區域範圍 54
4. 實驗設備與結果 56
4.1 實驗裝置 56
4.2 連續影像追蹤實驗 58
4.2.1 攝影機固定不動且無物體移動之情形 58
4.2.2 攝影機固定不動且有物體移動之情形 61
4.2.3 攝影機處於移動模式且無物體移動之情形 66
4.2.4 攝影機處於移動模式且有物體移動之情形 70
5. 結論與未來展望 79
參考文獻 81
自傳 85

[1]王聰榮、李繼泓，無人飛機發展現況與展望，機械工業雜誌281期，新竹，第58-59頁，2006。
[2]http://big5.xinhuanet.com/gate/big5/news.xinhuanet.com/mil/2012-06/21/c_123314440_2.htm(2014.3.12)
[3]Park, W. T. and Hill, J., “Real Time Control of a Robot with a Mobile Camera,” Proc. 9th ISIR, Washington, D.C., pp. 233-246, 1979.
[4]Hutchinson, S., Hager, G.D., and Corke, P.I., “A Tutorial on Visual Servo Control,” IEEE Trans on Robotics and Automation, Vol. 12, No. 5, pp.651-670, 1996.
[5]Allen, P.K., Timcenko, A., Yoshimi, B., and Michelman, P., Hand-Eye Coordination for Robotic Tracking and Grasping, in Hashimoto, K. (Ed.), Visual Servoing, World Scientific Publishing Co. Pte. Ltd., pp. 33-69,1993.
[6]Wilson, W.J., Visual Servo Control of Robots Using Kalman Filter Estimates of Robot Pose Relative to Work-Pieces, in Hashimoto, K(Ed.), Visual Servoing, World Scientific Publishing Co. Pte. Ltd., pp. 71-103, 1993.
[7]Feddema, J.T., Lee, C.S.G., and Mitchell, O.R., Feature-based Visual Servoing of Robotic System, in Hashimoto, K.(Ed.), Visual Servoing, World Scientific Publishing Co. Pte. Ltd., pp. 105-137, 1993.
[8]Hashimoto, K. and Kimura, H., LQ Optimal and Nonlinear Approaches to Visual Servoing, in Hashimoto, K.(Ed.), Visual Servoing, World Scientific Publishing Co. Pte. Ltd., pp. 165-197, 1993.
[9]張光寒、林世偉、楊筑鈞，“影像追蹤技術”，機器人世界情報網產業訊息，第1-17頁，2012年8月20日。
[10]Kim, C. and Hwang, J.N., “A Fast and Robust Moving Object Segmentation in Video Sequences,” in Proc. of the IEEE International Conference on Image Processing(ICIP’99), Vol. 2, Kobe, Japan, pp. 131-134, Oct. 1999.
[11]Kim, C. and Hwang, J.N., “Fast and Automatic Video Object Segmentation and Tracking for Content-Based Applications,” IEEE Transactions Circuits and Systems for Video Technology, Vol. 12, pp. 122-129, Feb. 2002.
[12]Lipton, A.J., Fujiyoshi, H., and Patil, R.S., “Moving Target Classification and Tracking from Real-Time Video,” in Proc. of the IEEE Workshop on Applications of Computer Vision, pp. 8-14, Oct. 1998.
[13]Horn, B.K.P., and Schunck, B.G., “Determining Optical Flow,” Artificial Intelligence, Vol. 17, pp.185-203, 1981.
[14]Barron, J., Fleet, D., and Beauchemin, S., “Performance of Optical Flow Techniques,” International Journal of Computer Vision, Vol.12, No.1, pp42-77, Jan. 1994.
[15]Singh, A., “Optical Flow Computation︰A Unified Perspective,” IEEE Computer Society Press, 1992.
[16]Anadan, P., “A Computational Framework and an Algorithm for Visual Motion,” International Journal of Computer Vision, Vol. 2, pp. 283-310, 1989.
[17]Zhu, S., and Ma, K.K., “A New Diamond Search Algorithm for Fast Block-Matching Motion Estimation, ” in Proc. 1997 Int. Conf. Information, Communication and Signal Processing(ICICS), Vol. 1, pp.292-296, Sept. 9-12, 1997.
[18]Koga, T., Iinuma, K., Hirano, A., Iijima, Y., and Ishiguro, T., “Motion Compensated Interframe Coding for Video Conferencing,”in Proc. Nat. Telecommunication Conf., pp. G5.3.1-G5.3.5, Nov.29 - Dec.3, 1981.
[19]Po, L.M., and Ma, W.C.,“A Novel Four-Step Search Algorithm for Fast Block Motion Estimation,” IEEE Trans. Circuits Syst. Video Technol., Vol. 6, pp. 313-317, June 1996.
[20]Lucas, B., and Kanade, T., “An Iterative Image Registration Technique With an Application to Stereo Vision,” Proc, DARPA Image Understanding Workshop, pp. 121-130, 1981.
[21]Simoncelli, E.P., Adelson, E.H., and Heeger, D.J., “Probability Distributions of Optical Flow,” Proc. Conf. Comput. Vis. Patt. Recog., Maui, pp. 310-315, 1991.
[22]McKenna, S., Jabri, S., Duric, Z., Rosenfeld, A., and Wechsler, H., “Tracking Groups of People,” Comput. Vis. Image Understanding, Vol. 80, No. 1, pp. 42–56, 2000.
[23]Peterfreund, N., “Robust Tracking of Position and Velocity With Kalman Snakes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.21, No. 6, pp. 564-569, Jun. 1999.
[24]Fujiyoshi, H. and Lipton, A.J., “Real-Time Human Motion Analysis by Image Skeletonization,” 4th IEEE Workshop on Applications of Computer Vision (WACV'98), October 19 - 21, 1998 , Princeton, New Jersey.
[25]Comaniciu, D., Ramesh, V., and Meer, P., “Kernel-Based Object Tracking”, Real-Time Vision & Modeling Dept., Siemens Corporate Res., Princeton, NJ, USA.
[26]Jang, D.S. and Choi, H.I., “Active Models for Tracking Moving Objects, ”Pattern Recognit., Vol. 33, No. 7, pp. 1135–1146, 2000.
[27]Karaulova, I.A., Hall, P.M., and Marshall, A.D., “A Hierarchical Model of Dynamics for Tracking People with a Single Video Camera,” in Proc. British Machine Vision Conf., pp. 262-352, 2000.
[28]Ju, S.X., Black, M.J., and Yaccob, Y., “Cardboard People: A Parameterized Model of Articulated Image Motion,” in Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, pp. 38-44, 1996.
[29]Dalal, N. and Triggs, B.,“Histograms of Oriented Gradients for Human Detection,”IEEE Conference Computer Vision and Pattern Recognition, Vol. 1, pp. 886-893, July 2005.
[30]Lowe, D.G., “Object Recognition from Local Scale-Invariant Features,”International Conference on Computer Vision, Vol. 60, 2004, pp. 1150-1157.
[31]Bay, H., Tuytelaars, T., and Gool, L.V.,“SURF:Speeded Up Robust Features,”Proceedings of European Conference on Computer Vision, 2006,pp.404-417.
[32]Rafael, C.G. and Richard, E.W., Digital Image Processing (3rd Edition), Prentice Hall, USA, 2007.
[33]Haralick, R.M. and Shapiro, L.G., “Computer and Robot Vision,” Vol. I, Addison-Wesley, 1992, pp.28-48.
[34]景雅新，“光流技術在移動物體影像追尋上之應用”，碩士論文，國立中山大學機械與機電工程學系，高雄，2003。
[35]郭志宏，“單眼視覺的行人偵測與追蹤”，碩士論文，國立中央大學資訊工程研究所，桃園，2011。