簡易檢索 / 詳目顯示

回結果列表
研究生： 陳毅安
I-An Chen
論文名稱： 場景結構之即時重建
Real-Time Scene Structure Reconstruction
指導教授： 林昌鴻
Chang-Hong Lin
口試委員: 吳晉賢
Chin-Hsien Wu
沈中安
Chung-An Shen
林淵翔
Yuan-Hsiang Lin
學位類別： 碩士
Master
系所名稱： 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年： 2013
畢業學年度： 101
語文別： 英文
論文頁數： 28
中文關鍵詞： 三維模型 、重建 、即時系統
外文關鍵詞： 3D model, reconstruction, real-time system
相關次數： 點閱：219  下載：4 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 本論文所提出的系統架構，著重在利用低成本之單鏡頭彩色攝影機，彈性地以手持方式移動，對場景結構進行即時三維表面模型重建。本論文所提出的方法，採用簡單且快速的演算法，並使其解析度落在人眼可接受範圍內，但所使用的演算法會產生大量的缺陷，因此系統會先挑選缺陷較少的結果，並利用其他演算法來大幅降低缺陷的影響。此外，本系統更被設計為少量資料即可運行的架構，因此只需少量的影像資料，即可產生完整的場景模型。本論文所提出的架構在根據不同的軟體與硬體設備進行最佳化後，將具有高度可程式化於嵌入式系統中的能力。

    The aim of the proposed method is to reconstruct the three-dimensional structure of a scene in real-time via moving a low-cost RGB mono-camera by hand. In the proposed method, only simple and fast algorithms are used for the purpose of real-time running with decent structure resolution. To compensate the defects of the cheap algorithms, the scene structures will be buffered and used only when they are under a good case, and they will be smoothed to decrease the effects of the structural defects. Even if the minority of overall cases is good cases, a complete scene structure can still be obtained with small amounts of different views. The proposed method can be applied into embedded systems after optimization and adjustment depending on different hardware and software.

    摘要...........................................................I Abstract.......................................................II 致謝...........................................................III List of Contents...............................................IV 1 Introduction.................................................1 1.1 Motivation.................................................1 1.2 Organization...............................................1 2 Related Works................................................2 2.1 Scene Based Reconstruction.................................2 2.3 Object Based Reconstruction................................3 3 Proposed Method..............................................5 3.1 Preprocessing..............................................5 3.2 Structure Estimation.......................................7 3.2.1 Motion Analysis..........................................7 3.2.2 Depth Estimation.........................................11 3.2.3 Structure Refinement.....................................15 3.3 Rendering..................................................17 3.3.1 Structure Rendering......................................17 3.3.2 User Interface...........................................19 4 Experiment Results...........................................20 4.1 Platform and Performance...................................20 4.2 Reconstructed Structure....................................21 5 Conclusions and Future Works.................................26 References.....................................................27

    [1] Y. Yang, H. Lin, and Y. Zhang, “Content-Based 3-D Model Retrieval: A Survey,” IEEE Transactions on Systems, Man, and Cybernetics - Part C: Applications and Reviews, vol. 37, no. 6, Nov. 2007.

    [2] J. J. Koenderink and A. J. van Doorn, “Affine structure from motion,” Affine structure from motion. J. Opt. Soc. Am., vol.8, issue 2, pp. 377-385, Feb. 1991.

    [3] R. A. Newcombe and A. J. Davison, “Live Dense Reconstruction with a Single Moving Camera,” IEEE Conference on Computer Vision and Pattern Recognition, 2010.

    [4] D. Hoiem, A. A. Efros, and M. Hebert, “Automatic Photo Pop-up,” ACM SIGGRAPH, 2005.

    [5] A. Wendel, M. Maurer, G. Graber, T. Pock, and H. Bischof, “Dense Reconstruction On–the–Fly,” IEEE Conference on Computer Vision and Pattern Recognition, 2012.

    [6] H. Chang and F. Tsai, “Reconstructing Three-Dimensional Specific Curve Building Models from a Single Perspective View Image,” International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XXXIX-B6, pp. 101-106, 2012.

    [7] S. Yu and M. Lhuillier, “Surface Reconstruction of Scenes Using a Catadioptric Camera,” Computer Vision/Computer Graphics Collaboration Techniques Lecture Notes in Computer Science, vol. 6930, pp. 145-156, 2011.

    [8] M. Pollefeys and L. V. Gool, “Stratified Self-Calibration with the Modulus Constraint,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 8, Aug. 1999.

    [9] M. Pollefeys, L. V. Gool, M. Vergauwen, F. Verbiest, K. Cornelis, J. Tops, and R. Koch, “Visual Modeling with a Hand-Held Camera,” International Journal of Computer Vision, vol. 59, issue 3, pp. 207-232, 2004.

    [10] K.-Y. K. Wong and R. Cipolla, “Reconstruction of Sculpture From Its Profiles With Unknown Camera Positions,” IEEE Transactions on Image Processing, 2004.

    [11] Q. Pan, G. Reitmayr, and T. Drummon, “ProFORMA: Probabilistic Feature-based On-line Rapid Model Acquisition,” In Proceedings of the British Machine Vision Conference, 2009.

    [12] C.-M. Cheng, S.-F. Wang, C.-H. Teng, and S.-H. Lai, “Image-Based Three-Dimensional Model Reconstruction from Chinese Treasure - Jadeite Cabbage with Insects,” Computers & Graphics, vol. 32, issue 6, pp. 682-694, Dec. 2008.

    [13] B. Lucas and T. Kanade, “An iterative image registration technique with an application to stereo vision,” In Proceedings of the International Joint Conference on Artificial Intelligence, pp. 674-679, 1981.

    [14] J. Shi and C. Tomasi, “Good Features to Track,” IEEE conference on Computer Vision and Pattern Recognition, pp. 593-600, June 1994.

    QR CODE