臺灣博碩士論文加值系統

近幾年來，整合電腦視覺與電腦圖學的研究方向大都集中在從攝影機擷取影片做虛擬世界景物的重建。
為了建造具備三維資訊的影片，從景物的取得、三維實景的重建到即時的互動呈現都是大家非常有興趣的研究課題。
為了能夠快速地重建出物體的三維模型，大多數的研究使用基於物體剪影的方法，但此方式所建構的三維模型常有細部資訊不足的缺點，
解決的方法之一就是增加剪影的影像數目。
而本篇論文主要探討在相機數量固定的情況下，對於移動的物體，使用反覆最近點演算法整合時間軸上的剪影資訊。
並使用視覺外殼的特性，自動改變移動評估時所設定的權重值，進而使得收斂的速度加快。
我們並把此一三維重建方式使用在絞接式物體的建構上。

In recent years, one of the major topics of computer vision and
computer graphics research is to reconstruct the real-world scenes
from video streams. In order to make immersive 3D video reality,
most researches focus on the scene acquisition, 3D reconstruction
and interactive real-time rendering. For fast 3D reconstruction of a
real scene, one of the commonly used techniques is
shape-from-silhouettes (SFS). However, SFS usually does not provide
detailed 3D information due to the available visible contours
acquired from limited viewpoints. One possible solution is to
increase the number of cameras, but this might significant increase
the cost and complexity of the video acquisition system. In this
thesis, we present a method for dynamic 3D reconstruction of
articulated objects. Given a fixed number of cameras used for video
acquisition, we use iterative closest point (ICP) algorithm to
integrate all of the acquired silhouette images of the object over
time. The convergence of ICP is sped up based on the weighting
derived from visual hull and motion estimation. Finally, a more
detailed 3D model can be achieved with the proposed approach.

1緒論
1.1研究動機
1.2相關研究及應用
1.3本篇重建方式的概述
1.4論文架構
2背景資料及相關原理
2.1相機幾何
2.2極線幾何（epipolar geometry）及基礎矩陣（fundamental matrix）
2.3利用剪影的三維重建技術（shape from silhouette, SFS）
2.4反覆最近點演算法（Iterative Closest Point, ICP）
3影像擷取
3.1相機校正
3.2前景及背景分割
3.3輪廓擷取及多邊形化
4三維模型的建立
4.1絞接式物體分割
4.2計算視覺邊線
4.3計算相接點
4.4計算物體的移動
4.5建立網狀連結
4.6紋理貼圖
5實驗結果
5.1實驗器材與場景架設
5.2剛體
5.2.1虛擬實驗
5.2.2實際實驗
5.3絞接式物體
5.3.1虛擬實驗
5.3.2實際實驗
6結論與未來展望

[1]S. Vedula, S. Baker, and T. Kanade, ``Image-Based Spatio-Temporal Modeling and View Interpolation of Dynamic Events,' ACM Transactions on Graphics, Vol. 24, No. 2, April, pp. 240 - 261, 2005.
[2]M. Li, H. Schirmacher, M. Magnor, H.-P. Seidel, ``Combining Stereo and Visual Hull Information for On-Line Reconstruction and Rendering of Dynamic Scenes,' IEEE Workshop on Multimedia Signal Processing, pp.9-12, 2002.
[3]G.K.M. Cheung,S. Baker, T. Kanade., ``Visual Hull Alignment and
Refinement Across Time: a 3D Reconstruction Algorithm Combining Shape-from-Silhouette with Stereo,' Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 375-382, 2003.
[4]A. Laurentini, ``The Visual Hull Concept for Silhouette-Based Image Understanding,' IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.150-162, 1994.
[5]E. Trucco and A. Verri, Introductory Techniques for 3-D Computer Vision, Prentice-Hall, USA, 1998.
[6]R.Y. Tsai, ``A Versatile Camera Calibration Technique for High-Accuracy 3D Machine Vision Metrology Using Off-The Shelf TV Cameras and Lenses,' IEEE Journal of Robotics and Automation, pp. 323-344, August 1987.
[7]C. Hernandez Esteban, F. Schmitt., ``Multi-Stereo 3D Object Reconstruction,' Proceedings of International Symposium on 3D Data Processing, Visualization and Transmission, pp. 159-166,2002.
[8]N. Amenta and R. Kolluri, ``The Power Crust,' ACM Symposium on Solid Modeling and Applications, pp. 249-260, 2001.
[9]Z. Zhang, ``A Flexible New Technique for Camera Calibration,' Technical Report, Microsoft Research Technical Report MSRTR- 98-71,1998.
[10]T. Terauchi, Y. Oue, and K. Fujimura, ``A Flexible 3D Modeling System Based on Combining Shape-from-Silhouette,' Proceedings of International Conference on 3-D Digital Imaging and Modeling, pp.196-203, 2005.
[11]W. Matusik, C. Buehler, R. Raskar, L. McMillan, and S. Gortler, ``Image-Based Visual Hulls,' Proceedings of ACM SIGGRAPH, pp. 369-374. 2000.
[12]S.D. Roeck, N. Cornelis, ``Augmenting Fast Stereo with Silhouette Constraints for Dynamic 3D,' Proceedings of IEEE International Conference on Pattern Recognition, pp. 131-134,2006.
[13]J. Allard, J.-S. Franco, C. Menier, E. Boyer, and B. Raffin, ``The GrImage Platform: A Mixed Reality Environment for Interactions,' Proceedings of IEEE International Conference on Computer Vision Systems, 2006.
[14]P. Besl and N. McKay, ``A Method of Registration of 3D Shapes,' IEEE Transaction on Pattern Analysis and Machine Intelligence, pp. 239-256, February 1992.
[15]Z. Zhang, ``Iterative Point Matching for Registration of Free-Form Curves and Surfaces,' International Journal of Computer Vision, pp. 119-152, October 1994.
[16]S. Rusinkiewicz and M. Levoy, ``Efficient Variants of the ICP Algorithm,' International Conference on 3D Digital Imaging and Modeling, pp. 145-152, May 2001.
[17]H. Ebrahimnezhad and H. Ghassemian, ``Combining the Feature based Stereo Matching, Motion and Silhouette to Reconstruct Visual Hull,' IEEE Workshop on Signal Processing Systems Design and Implementation, pp. 461- 466, Nov 2005.
[18]G.K.M. Cheung, S. Baker, J. Hodgins, and T. Kanade, ``Markerless Human Motion Transfer,' Proceedings of 2nd International Symposium on 3D Data Processing, Visualization and Transmission, pp. 373- 378, Sept 2004.
[19]L. Guan, J.-S. Franco, and M. Pollefeys, ``3D Occlusion Inference from Silhouette Cues,' IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, June 2007.
[20]S. Petitjean, ``A Computational Geometric Approach to Visual Hulls,' International Journal of Computational Geometry and Applications, pp. 407-436, 1998.
[21]B. Baumgart, ``Geometric Modeling for Computer Vision,' Technical Report, Stanford University. Ph.D. Thesis. Department of Computer Science. 1974.
[22]R. Szeliski, ``Rapid Octree Construction from Image Sequences,' Computer Vision, Graphics, and Image Processing: Image Understanding, pp. 23-32, 1993.
[23]S. Srivastava, and N. Ahuja, ``Octree Generation from Object Silhouettes in Perspective Views,' Computer Vision, Graphics and Image Processing, pp. 68-84, 1990.
[24]T. Matsuyama, X. Wu, T. Takai, and S. Nobuhara, ``Real-Time 3D Shape Reconstruction, Dynamic 3D Mesh Deformation, and High Fidelity Visualization for 3D Video,' Computer Vision and Image Understanding, pp. 393-434, 2004.
[25]W. Lorensen, and H. Cline, ``Marching Cubes: A High-Resolution 3D Surface Construction Algorithm,' Proceedings of ACM SIGGRAPH, pp. 163-170, 1987.
[26]E. Boyer, and J.-S. Franco, ``A Hybrid Approach for Computing Visual Hulls of Complex Objects,' Proceedings of IEEE Conference on Computer Vision and Pattern Recognition , pp. 695-701, 2003.
[27]J.-S. Franco, and E. Boyer, ``Exact Polyhedral Visual Hulls, Proceedings of Conference British Machine Vision, pp.329-338, 2003.
http://perception.inrialpes.fr/~Franco/EPVH/index.php.
[28]W. Matusik, C. Buehler, R. Raskar, L. McMillan, and S. Gortler, ``A Target Dependent Colorspace for Robust Tracking,' Proceedings of IEEE International Conference on Pattern Recognition, Vol. 3, pp. 43-46, 2006.
[29]D.H. Douglas and T.K. Peucker, ``Algorithms for the Reduction of the Number of Points-Required to Represent a Line or its Caricature,' The Canadian Cartographer, pp. 112-122, 1973.
[30]N. Amenta, S. Choi, and R. Kolluri, ``Power Crust, Unions of Balls, and the Medial Axis Transform,' Computational Geometry: Theory and Applications, pp. 127-153, 2001.
[31]URL: http://public.kitware.com/VTK/