| 研究生: |
吳孟蓉 Wu, Meng-jung |
|---|---|
| 論文名稱: |
藉由變形三維人頭模型重建人臉 Face Reconstruction by Deforming 3D Head Model |
| 指導教授: |
連震杰
Lien, Jenn-jier James |
| 學位類別: |
碩士 Master |
| 系所名稱: |
電機資訊學院 - 資訊工程學系 Department of Computer Science and Information Engineering |
| 論文出版年: | 2007 |
| 畢業學年度: | 95 |
| 語文別: | 英文 |
| 論文頁數: | 50 |
| 中文關鍵詞: | 攝影機 、模型 、重建 |
| 外文關鍵詞: | sequence, image, model, EM, 3D-2D-2D, 3D-2D |
| 相關次數: | 點閱:62 下載:2 |
| 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 |
建立一個真實的三維人臉模型在電腦視覺這個領域裡面一直以來都是一項挑戰。我們發展了一套系統,讓我們可以容易又有效率的重建出三維人臉模型。我們這個系統使用單一個攝影機(普通的攝影機或是網路攝影機都可以)來擷取人臉在攝影機前面做轉動動作的影片之後,選取一些特徵點,利用基礎關係演算法(correlation-basedalgorithm)來做追蹤,找到在每一個畫面裡面每一個特徵點的對應點之後,在沒有消失點的情況之下,選擇使用方法一:3D-2D或是方法二:3D-2D-2D重建三維人臉。在具有消失點的情況之下,可利用方法三:EM重建三維人臉,使系統功能更為完善。
Generating realistic three-dimensional (3D) human face models has been a persistent challenge in computer vision. We developed a system that can easily and efficientlyreconstruct 3D faces. The system takes a video sequence of the face having a pan rotation from one single regular camera. Based on the corresponding points tracked by correlation-based algorithm, we can choose first: 3D-2D or second approach: 3D-2D-2D to reconstruct the 3D face in the situation with no missing points. On other hand, third approach: EM provides us an algorithm to reconstruct the 3D face under having missing points. It makes our system become better.
[1] A. Tankus, N. Sochen, and Y. Yeshurun, “A New Perspective [on] Shape-from-Shading”, IEEE ICCV, Vol. II, pp. 862–869, 2003.
[2] C. J. Taylor, D. J. Kriegman, and P. Anandan, “Structure and motion in two dimensions from multiple images: A least squares approach”, In IEEE Workshop on Visual Motion, pp. 242–248, October 1991.
[3] C. Tomasi and T. Kanade, “Shape and Motion from Image Streams under Orthography: a Factorization Method”, IJCV, 9(2), pp. 137-154, 1992.
[4] J. Costeira and T. Kanade, “A multi-body factorization method for motion analysis”, In ICCV, pages 1071–, 1995.
[5] P. Fua. A Parallel, “Stereo Algorithm that Produces Dense Depth Maps and Preserves Image Features”, Machine Vision and Applications, 6(1):35–49,Winter 1993.
[6] P. Fua, “Regularized Bundle-Adjustment to Model Heads from Image Sequences without Calibration Data”, IJCV, pp. 153-171, July 2000.
[7] R. Zhang, P.S. Tsai, J.E. Cryer, and M. Shah, “Shape from Shading: A Survey”, IEEE Transactions on PAMI, 21(8), pp.690–705, 1999.
[8] R. Y. Tsai and T. S. Huang, “Uniqueness and estimation of three dimensional motion parameters of rigid objects with curved surfaces”, IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-6(1):13–27, January 1984.
[9] R. Hassanpour, V. Atalay, “Delaunay Triangulation based 3D Human Face Modeling from Uncalibrated Images,” CVPRW, pp.75, June 2004.
[10] S. Ullman, “The Interpretation of Visual Motion”, MIT Press, Cambridge, Massachusetts, 1979.
[11] S. Roweis, “EM algorithms for PCA and SPCA”, In NIPS, pages 431–437, 1997.
[12] Zhengyou Zhang, “A Flexible New Technique for Camera Calibration”, Microsoft, 1999.