本論文主要研究目的是利用立體視覺計算出物體在空間到攝影機的距離，再利用反投影將影像中的物體還原到三維空間中以求解出目標物體的輪廓。而立體視覺中最重要的工作即是立體匹配，匹配的結果將會影響著物體的距離精度。本文提出利用銳利化遮罩將原始圖片做銳利化，以及改變匹配的窗口大小，藉由上述條件找出最適當之組合來求解出目標物輪廓。為了增加匹配速度與精度，本文首先利用SURF演算法找出影像中的特徵點估計出基本矩陣，基本矩陣即表示兩張圖片的對應關係。利用極線幾何原理將左右兩張圖片做扭曲校正。校正過後的圖片具有極軸水平且極軸等高的特性，進而增加匹配的精度與速度。最後使用快速正規劃交互相關性演算法完成影像中匹配的工作。本文實驗部份選擇了五組不同的銳化程度以及三種不同的窗口大小，共十五組實驗數據來探討銳利化以及各種匹配窗口大小對立體匹配精準度的影響。實驗結果顯示，當窗口過小時匹配錯誤率會大幅的提高，反之窗口夠大則會增加匹配的準確度與速度。而銳化過後影像匹配的精度則是比原本的高出許多。

In this thesis, we will explain how we can use stereo vision to estimate the distance between the object and camera. By using back projection method to 3-D space, we recover existing two images to analyze the contour of the object. Stereo matching is the most important step of stereo vision as it will determine the accuracy of our experimental result- estimated distance between the camera and the object. Besides, we will also be using unsharp mask filter to sharpen images and altering window sizes to find the best way to improve the accuracy and speed of stereo matching in our experiment.
In the first part of thesis, we will explore how SURF algorithm is used to extract feature points and how use methods to estimate the fundamental matrix and the corresponding relationship between two images. Next, we use epipolar geometry to rectify two images and prove that the epipolar lines of rectified images are parallel and have the same height.
Last but not at least, we use FNCC to match two images. This experimental results demonstrate that the smaller the window is the more errors stereo matching occur and vice versa, the bigger the window is the more actual result you get- sharpen images will be clearer than the original images.

[1] J. Zhao, S. Chang, and Z. M. Guo, "3D Reconstruction based on the Matching Method of GA," in Machine Learning and Cybernetics (ICMLC), 2010 International Conference on, Qingdao, 2010, pp. 1798 - 1801.
[2] T. Li, G. Yuan, and Q. Duan, "Navigation Technology of Autonomous Mobile Robots in Unknown Environments," in Mechatronics and Embedded Systems and Applications (MESA), 2010 IEEE/ASME International Conference on, 2010, pp. 533-538.
[3] J. C. Andersen, N. A. Andersen, and R. Ole, "Trinocular Stereo Vision for Intelligent Robot Navigation," in Proceedings of the 5th IFAC/EURON Symposium on Intelligent Autonomous Vehicles, Lisboa, Portugal, 2004.
[4] A. L. Hou, X. Cui, Y. Geng, W. J. Yuan, and J. Hou, "Measurement of Safe Driving Distance Based on Stereo Vision " in Image and Graphics (ICIG), 2011 Sixth International Conference on Hefei, Anhui 2011, pp. 902 - 907.
[5] K. Muljowidodo, A. R. Mochammad, N. SaptoAdi, and B. Agus, "Vision based Distance Measurement System using Single Laser Pointer Design for Underwater Vehicle," Indian Journal of Marine Sciences (IJMS), 2009, vol. 38, pp. 324-331.
[6] J. Mrovlje and D. Vrancic, "Distance Measuring based on Stereoscopic Pictures," presented at the 9th International PhD Workshop on Systems and Control: Young Generation Viewpoint Izola, Slovenia, 2008.
[7] H.-S. Baek, J.-M. Choi, and B.-S. Lee, "Improvement of Distance Measurement Algorithm on Stereo Vision System (SVS) " in Ubiquitous Information Technologies and Applications (CUTE), 2010 Proceedings of the 5th International Conference on Sanya, 2010, pp. 1 - 3.
[8] X. Xu and J. Zhang, "The Method of Image Matching by Taking Every Fixed Match Pixel," presented at the Computational Intelligence and Design (ISCID), 2012 Fifth International Symposium on, Hangzhou 2012.
[9] L. D. Stefano, M. Marchionni, and S. Mattoccia, "A Fast Area-Based Stereo Matching Algorithm," Image and Vision Computing, 2004, vol. 22, pp. 983 - 1005.
[10] D. Scharstein and R. Szeliski, "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms," International Journal of Computer Vision, 2002, vol. 47, pp. 7-42.
[11] H. Zhang and X. Wei, "An Image Matching Algorithm based on FAST and Sub-Pixel Accuracy," in Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC), 2011 2nd International Conference on Deng Leng 2011, pp. 3736 - 3739.
[12] M. Hariti, Y. Ruichek, and A. Koukam, "A Voting Stereo Matching Method for Real-Time Obstacle Detection " in Robotics and Automation, 2003. Proceedings. ICRA '03. IEEE International Conference on Taipei, Taiwan, 2003, pp. 1700-1704.
[13] Z. Ahmed, A. J. Hussain, and D. Al-jumeily, "Edge Detection for Fast Block-Matching Motion Estimation to Enhance Mean Predictive Block Matching Algorithm," in Innovations in Intelligent Systems and Applications (INISTA), 2012 International Symposium on Trabzon 2012, pp. 1 - 5.
[14] Wikipedia. (15 January 2014 07:42 UTC). Computer vision, Wikipedia, The Free Encyclopedia. Available: http://en.wikipedia.org/w/index.php?title=Computer_vision&oldid=583700035
[15] K. Yoshida and S. Hirose, "Real-Time Stereo Vision with Multiple Arrayed Camera," in Robotics and Automation, 1992. Proceedings., 1992 IEEE International Conference on Nice, France, 1992, pp. 1765 - 1770.
[16] M. Okutomi and T. Kanade, "A Multiple-Baseline Stereo," in Computer Vision and Pattern Recognition, 1991. Proceedings CVPR '91., IEEE Computer Society Conference on Maui, HI 1993, pp. 63 - 69.
[17] M. A. Muquit, T. Shibahara, and T. Aoki, "A High-Accuracy Passive 3D Measurement System Using Phase-Based Image Matching," IEICE Trans. Fundam. Electron. Commun. Comput. Sci., vol. E89-A, pp. 686 - 697, 2006.
[18] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Second ed.: Cambridge University Press, 2003.
[19] Q.-T. Luong, R. Deriche, O. Faugeras, and T. Papadopoulo, On Determining the Fundamental Matrix : Analysis of Different Methods and Experimental Results, 1993.
[20] Z. Y. Zhang, "Determining the Epipolar Geometry and its Uncertainty: A Review," International Journal of Computer Vision, 1998, vol. 27, pp. 161 - 195.
[21] V. Nozick, "Multiple View Image Rectification," in Access Spaces (ISAS), 2011 1st International Symposium on Yokohama 2011, pp. 277-282.
[22] C. Loop and Z. Zhang, "Computing Rectifying Homographies for Stereo Vision," in Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on, Fort Collins, CO 1999, pp. 125-131.
[23] R. I. Hartley, "Theory and Practice of Projective Rectification," International Journal of Computer Vision, vol. 35, pp. 115 - 127, 1999.
[24] D. G. Lowe, "Object Recognition from Local Scale-Invariant Features," in Proceedings of the International Conference on Computer Vision, 1999, vol.2, p. 1150.
[25] D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," Int. J. Comput. Vision, 2004, vol. 60, pp. 91-110.
[26] H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, "SURF: Speeded Up Robust Features," Computer Vision and Image Understanding (CVIU), 2008, vol. 110, pp. 346-359.
[27] S. Sha, J. Chen, and S. Luo, "A Fast Matching Algorithm based on K-degree Template," in Computer Science & Education, 2009. ICCSE '09. 4th International Conference on, 2009, pp. 1967-1971.
[28] A. Klaus, M. Sormann, and K. Karner, "Segment-Based Stereo Matching Using Belief Propagation and a Self-Adapting Dissimilarity Measure," in Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, 2006, pp. 15-18.
[29] T. Shibahara, T. Aoki, H. Nakajima, and K. Kobayashi, "A Sub-Pixel Stereo Correspondence Technique Based on 1D Phase-only Correlation," in Image Processing, 2007. ICIP 2007. IEEE International Conference on, 2007, pp. V - 221-V - 224.
[30] Y.-F. Liao, "Object Geometry Reconstruction by Stereo Image Data ", Department of Aeronautics and Astronautics, National Cheng Kung University, 1995.
[31] Wikipedia. (2014, 15 January 2014 03:45 UTC ). Pinhole camera, Wikipedia, The Free Encyclopedia. Available: http://en.wikipedia.org/w/index.php?title=Pinhole_camera&oldid=590641941
[32] C. i. Colour. (20 December). Cambridge in colour. Available: http://www.cambridgeincolour.com/tutorials/image-sharpening.htm
[33] T. S. Hsu and T. C. Wang, "An Improved Stereo Vision Image Processing for Object Distance Measurement," in The 12th International Conference on Automation Technology, 2013.
[34] R. Lienhart and J. Maydt, "An Extended set of Haar-Like Features for Rapid Object Detection," in Image Processing. 2002. Proceedings. 2002 International Conference on, 2002, vol.1, pp. I-900-I-903.
[35] J. P. Lewis, "Fast Normalized Cross-Correlation," in Vision Interface, Quebec, Canada, 1995, pp. 120-123.
[36] H. C. Longuet-Higgins, " A Computer Algorithm for Reconstructing a Scene from Two Projections," in Readings in computer vision: issues, problems, principles, and paradigms, A. F. Martin and F. Oscar, Eds., ed: Morgan Kaufmann Publishers Inc., 1987, pp. 61-62.
[37] R. I. Hartley, " In Defense of the Eight- Point Algorithm," in Pattern Analysis and Machine Intelligence, IEEE Transactions on 1997, pp. 580 - 593
[38] M. A. Fischler and R. C. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography," in Readings in computer vision: issues, problems, principles, and paradigms, A. F. Martin and F. Oscar, Eds., ed: Morgan Kaufmann Publishers Inc., 1987, pp. 726-740.
[39] Wikipedia. (15 January 2014 07:40 UTC ). RANSAC, Wikipedia, The Free Encyclopedia. Available: http://en.wikipedia.org/w/index.php?title=RANSAC&oldid=583866975