在電腦視覺的領域中，三維物體的辨識與立體視覺是一項重要的工作。在本論文中，我們使用尺度不變性特徵轉換（Scale Invariant Feature Transform, SIFT）來尋找三維物體的特徵，並利用顯示卡運算能力來達成即時運算能力。由於SIFT特徵本身良好的旋轉不變性、尺度不變性（scale-invariance）和抵抗背景雜訊的特性，我們的偵測器便可以達到旋轉不變性，並可以讓物體以不同大小出現時都能被偵測，因為每個物體都有其獨特的特徵，所以我們利用每個物體獨特的特徵來辨識物體，並利用對應矩陣來計算不同平面的旋轉角度。在本論文中，除了利用SIFT方法來即時辨識三維物體外，還加入了立體視覺原理來判斷三維物體與攝影機的距離，並利用物體的位置、不同平面角度與深度資訊來控制機械手臂指出物體。

3-D object recognition and stereo vision are important tasks in computer vision. In this thesis, we use Scale Invariant Feature Transform (SIFT) to search 3-D object features and use GPU to perform the real-time capability. Since SIFT has rotation-invariant, and scale-invariant characteristics, and can handle complex backgrounds, our detector can detect objects of different sizes based on its own unique feature. The corresponding homography is used to calculate the out-plane orientations. In this thesis, we implement the SIFT algorithm to recognize the 3-D objects and also use the stereo vision theorem to determine the distance form the cameras to the object. A robot arm is controlled to point to the object based on the orientations, and depth information of the object.

[1] Jia Wang, Wen-jann Yang and Raj Acharya. “Color Clustering Techniques for Color-Content-Based Image Retrieval from Image Databases,” Proceedings of IEEE International Conference on Multimedia Computing Systems, 1997, pp. 442-449.

[2] Wei-Ying Ma and Hong Jiang Zhang. “Benchmarking of image features for content-based retrieval,” Proceedings of the Thirty-Second Asilomar Conference on Signals, Systems & Computers, vol. 1 , 1998, pp. 253–257.

[3] Huang J., S Ravi Kumar, Mandar Mitra, Wei-Jing Zhu, Ramin Zabih. “Image Indexing Using Color Correlograms,” Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, 1997, pp. 762-768.

[4] Hideyuki Tamura, Shunji Mori, and Takashi Yamawaki. “Textural Features Corresponding to Visual Perception,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 8, No. 6, Jun. 1978.

[5] Mikolajczyk, K. , Zisserman, A. and Schmid, C. “Shape recognition with edge-based features”, Proceedings of the British Machine Vision Conference, 2003

[6] R. Singh, I. Pavlidis, and N. P. Papanikolopoulos, “Recognition of 2D Shapes through Contour Metamorphosis,” Proceeding of the 1997 IEEE International Conference on Robotics and Automation, pp.1651-1656.

[7] D. Marr and T. Poggio, “Cooperative computation of stereo disparity,” Science, Vol. 194, 1976, pp. 283-287.

[8] S.T. Barnard and W.B. Thompson, “Disparity analysis of images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 2, 1980, pp. 330-340.

[9] Andreas Klaus, Mario Sormann and Konrad Karner, “Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure,” Proceedings of the 18th International Conference on Pattern Recognition, Vol. 03, 2006, pp.15-18.

[10] David G. Lowe, “Object Recognition from Local Scale-Invariant Features,” Proceedings IEEE International Conference Computer Vision, vol. 2, 1999, pp. 1150-1157.

[11] David G. Lowe, “Local feature view clustering for 3D object recognition”. Proceedings IEEE Conference Computer Vision and Pattern Recognition, vol. 1, 2001, pp. 682-688.

[12] David G. Lowe, “Distinctive Image Features from Sacle-Invariant Keypoints,” International Journal of Computer Vision, 2004, vol. 60, no. 2, pp. 91-110.

[13] Camera Calibration Toolbox Web Site at http://www.vision.caltech.edu/bouguetj/index.html

[14] R. C. Gonzalez and R. E. “Woods, Digital image processing,” Addison Wesley, 1993.

[15] Harris, C. and Stephens, M. “A combined corner and edge detector,” Fourth Alvey Vision Conference. Manchester, 1988, UK : 147-151.

[16] P. V. C. Hough, “Method and means for recognizing complex patterns ,” U. S. Patent 3,069,654, 1962.

[17] D. H. Ballard, "Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, vol. 13, n. 2, 1981, pp. 111-122.

[18] Brown, M. and Lowe, D.G. “Invariant features from interest point groups,” In British Machine Vision Conference, Cardiff, Wales, 2002, pp. 656-665.

[19] Richard Szeliski, “Image alignment and stitching: A tutorial,” Technical Report MSR-TR-2004-92, Microsoft Research, December 2004.

[20] R. Sukthankar, R. G. Stockton, M. D. Mullin, "Automatic Keystone Correction for camera-assisted Presentation interface", Proceedings of International Conference on Multimedia Interfaces, pp. 601-714, 2000

[21] Richard Hartley and Andrew Zisserman, “Multiple view geometry in computer vision,” Cambridge University, Cambridge, 2nd edition, 2003.

[22] General-Purpose Graphic Processing Unit, http://www.gpgpu.org/

[23] GPU Shader language source code, http://sourceforge.net/

[24] SIFT on GPU source code, http://cs.unc.edu/~ccwu