本論文主要在於討論在模擬場景下的塔台辨識，利用模擬雷射測距儀來拍攝 塔台，用來得到距離影像與點雲資料，本論文有效的提出結構描述子與視角內插 法搭配傅立葉描述子，也在第四章根據距離的遠近來做比較，距離足夠近時利用 結構描述子，距離足夠遠時利用視角內插法搭配傅立葉描述子，最後再將這兩個 方法做合併提出一整合型方法可應用在距離從遠到近的變化，本論文所利用的結 構描述子與傅立葉描述子擁有較快的特徵抽取的速度，只要硬體設備的強化與軟 體方面做平行運算與最佳化的動作，本論文系統更可以達到使用者所需之時間要 求，但由於本論文在距離足夠近時，所使用之特徵都只有塔台的幾何特性與結構 特性，並沒有考慮到物體的材質與顏色的特性，而在距離足夠遠時只考慮塔台的 輪廓特性，並沒有考慮其深度資訊，且本論文在進行辨識時，都只有考慮當前的 資訊，並無考慮以前的資訊，即只使用單一時間點的觀測是不足的，循序估測是 必要的，例如本論文在第四章中第八部分所討論的相機姿態就是一個資訊，通常 在一個飛行軌跡中相機的姿態變化應該是連續的，即姿態變化不能太過劇烈，由 於本論文並無考慮以前的資訊，故在辨識正確率上無法有更好的突破。
所以在未來的發展上可以分成三個方向，首先在距離足夠近時，當使用點雲 資料時，不僅考慮塔台的幾何與結構資訊，也對其點雲資料賦予顏色或是材質的 資訊，第二個方向在於距離足夠遠時，不僅考慮輪廓的變化，也需要考慮深度的 變化問題，最後第三個方向在於進行辨識時可以加入以前的資訊，考慮了上述三 個方向，以及加入這些特性將可以提升本論文對於辨識系統的強健性，希望能夠 應用在真實的塔台上，來測詴本論文的效能，當然，應用在真實的場景中就必頇 先把塔台分割出來，以便於辨識時使用。
71
參考文獻
[1] D. S. Zhang and G. J. Lu, “A comparative study on shape retrieval using Fourier descriptors with different shape signatures,” in Proceedings of the International Conference on Multimedia and Distance Education, Fargo, North Dakota, USA, June 2001, pp. 1-9.
[2] W. Y. Kim and Y. S. Kim, “A region-based shape descriptor using Zernike moments,” Signal Processing Image Communication, vol. 16, pp. 95-102, 2000.
[3] D. S. Zhang and G. Lu, “An integrated approach to shape based image retrieval,”
in Proceeding of 5th Asian Conference on Computer Vision, Melbourne, Australia, 2002, pp. 652-657.
[4] R. Osada, T. Funkhouser, B. Chazelle, and T. Seidl, “Shape distributions,” ACM Transactions on Graphics, vol.21, no. 4, pp. 807-832, 2002.
[5] A. E. Johnson and M. Hebert, “Using spin image for efficient object recognition in cluttered 3D scenes,” IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 21, no. 5, pp. 433-449, May 1999.
[6] C. Dorai and A. Jain, “Cosmos - a representation scheme for 3D free form objects,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol.
19, no. 10, pp. 1115-1130, October 1997.
[7] T. J. Fan, G. Medioni, and R. Nevatia, “Recognizing 3D objects using surface descriptions,” IEEE Transactions on Pattern Analyses and Machine Intelligence, vol. 11, pp. 1140-1157, November 1989.
[8] S. Biasotti, S. Marini, and M. Spagnuolo, B. Falcidieno, “Sub-part correspondence by structural descriptors of 3D shapes,” Computer-Aided Design, vol. 38, no. 9, 2006, pp. 1002-1019.
[9] S. Marini, S. Biasotti, and B. Falcidieno, “Partial matching by structural descriptors,” in Proceedings of Content-based Retrieval, Dagsthul, Germany, 2006.
[10] M. Kazhdan, T. Funkhouser, and S. Rusinkiewic, “Rotation invariant spherical harmonic representation of 3D shape descriptors,” in Proceedings of ACM/Eurographics Symposium on Geometry Processing, Aachen, Germany, 2003, pp. 156-164.
[11] H. Sundar, D. Silver, N. Gagvani, and S. Dickinson, “Skeleton based shape matching and retrieval,” in Proceeding of International Conference on Shape Modeling and Application, Seoul, Korea , May 2003, pp. 130-139.
[12] A. Bucksch and H. A. Wageningen, “Skeletonization and segmentation of point clouds using octrees and graph theory,” Symposium Image Engineering and Vision Metrology, Dresden, Germany, vol. 36, pp. 1-6, 2006.
72
[13] H. Blum, “A transformation for extracting new descriptors of shape,” in Proceedings of the Symposium, Cambridge, Massachusetts, 1967, pp. 362-280 [14] 徐道智，「以主成分影像作特徵抽取之三維模型檢測系統」，國立交通大學，
碩士論文，民國98年7月
[15] I. Kunttu and L. Lepisto, “Shape based retrieval of industrial surface defects using angular radius Fourier descriptor,” IET Image Processing, vol. 1, no. 2, pp.
231-236, 2007.
[16] S. Gumhold, X. Wang, and R. McLeod, “Feature extraction from point clouds,”
in Proceedings of 10th International Meshing Roundtable, Sandia National Laboratories, Newport Beach, California, October 2001, pp. 293-305.
[17] G. H. Bendels, R. Schnabel, and R. Klein, “Detecting Holes in Point Set Surfaces,” The Journal of WSCG, vol. 14, pp. 8996, 2006.
[18] D. L. Page, Y. Sun, J. Paik, and M. A. Abidi, “Normal vector voting: Crease detection and curvature estimation on large, noisy meshes,” Graphical Model, vol. 64, no. 3-4, May/July 2002, pp. 199-229.
[19] G. Hetzel, B. Leibe, P. Levi, and B. Schiele, “3D object recognition from range images using local feature histograms,” in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, USA, vol. 2, pp. 394-399, 2001.
[20] T. Rabbani, F. Heuvel, and G. Vosselmann, “Segmentation of point clouds using smoothness constraint,” in International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 36, part 5, Dresden, Germany, September 2006, pp. 248-253.
[21] J. Wang and J. Shan, “Segmentation of lidar point clouds for building extraction,”
in Proceedings American Society Photogrammetry and Remote Sensing Annual Conference, Baltimore, Maryland, March 2009, pp. 9-13.
[22] E. Bengoetxea, “Inexact Graph Matching Using Estimation of Distribution Algorithms,” Ph. D. dissertation, Basque, France, December 2002.
[23] H. Bunke, “Error Correcting Graph Matching: On the Influence of the Underlying Cost Function,” IEEE Transaction Pattern Analysis and Machine Intelligence, vol. 21, no. 9, pp. 917-922, September 1999.
[24] A. Hlaoui and S. Wang, “A New Algorithm for Inexact Graph Matching,” in Proceedings of the 16th International Conference on Pattern Recognition, Quebec, Canada, vol. 4, 2002, pp. 180-183.
[25] A. Hlaoui and S. Wang, “A new algorithm for graph matching with application to content-based image retrieval,” in Proceedings of the Joint IAPR International Workshops SSPR and SPR, Windsor, Ontario, Canada, vol. 2396, 2002, pp.
291-300.
73
[26] J. R. Ullman, “An algorithm for subgraph isomorphism,” Journal of the ACM, vol. 23, no. 1, January 1976, pp. 31-42.
[27] P.S. Mayback, Stochastic Models, Estimation, and Control, New York:
Academic, 1982.
[28] S. I. Roumeliotis, G. S. Sukhatme, and G. A. Bekey, “Circumventing dynamic modeling: Evaluation of the error-state kalman filter applied to mobile robot localization,” in Proceedings of IEEE International Conference in Robotics and Automation, Detroit, Michigan, USA, 1999, pp. 1656-1663.
[29] R. E. Kalman, “A New Approach to Linear Filtering and Prediction Problems,”
Transaction of the American Society of Mechanical Engineers - Journal of Basic Engineering, vol. 82, pp. 35-45, 1960.
[30] T.Tou, “A dynamic optimal cluster,” International Journal of Computer and Information Sciences, vol. 8, no. 6, pp. 541-547, 1979
[31] Zhu. X, “Shape recognition based on skeleton and support vector machines,” in Proceeding of the 3th International Conference on Intelligent Computing, 2007, pp. 1035-1043.
[32] R.B. Rusu, Z.C. Marton, N. Blodow, M. Beetz, “Persistent point feature histograms for 3D point clouds,” in Proceeding of the 10th International Conference on Intelligent Autonomous System, Baden-Baden, Germany, 2008, pp. 119-128.