臺灣博碩士論文加值系統

傳統的立體影像生成經常使用多台彩色攝影機拍攝而成，隨著各式各樣深度擷取設備的上市，使用彩色與深度影像成為立體影像生成的另一途徑。在生成過程中，容易因視點遮蔽或反射材質等問題而產生空洞。本研究以RGB-D攝影機取得彩色與深度影像為基礎，探討生成立體影像之技術並對空洞進行填補。首先深度影像經過前處理後，將深度影像與彩色影像採用深度繪圖法，分別生成左右眼影像。接著，將左右眼影像運用改良後的修補方法修復空洞，並利用頭戴顯示器觀看修補後的左右眼影像，以驗證其立體成效。

Traditional stereoscopic images are generated using multiple color-cameras. With the popularity of depth capture devices, it becomes a possible way to generate stereoscopic images by use of color and depth images. During the generating process, holes are created because of visual occlusion or reflective material. Based on color and depth images from RGB-D camera, this study explores the technology of generating stereoscopic images and filling the holes. First, use the DIBR algorithm to generate the left-eye and right-eye images respectively, and then propose an improved inpainting method to fill the hole. To verify the actual effect of stereoscopic images, the head-mounted display is used to view the inpainted stereoscopic images.

第一章 簡介 1
1.1研究背景 1
1.2研究動機與目的 2
第二章 文獻探討 3
2.1 Kinect體感裝置 3
2.2三維立體影像顯示 6
2.2.1眼鏡式立體顯示器 7
2.2.2裸眼式立體顯示器 8
2.3影像修補 10
2.4立體影像修補 11
2.4.1基於圖像金字塔之修補方法 11
2.4.2快速行進演算法 12
2.4.3水平內插法 12
2.4.4深度影像平滑化 12
2.5深度繪圖法 13
第三章 研究方法 14
3.1前處理 14
3.2三維影像形變 16
3.3空洞填補 18
第四章 實驗結果 21
4.1實驗一 21
4.2實驗二 23
4.2實驗三 25
第五章 結論與未來工作 28
參考文獻 29

[1]Safae Elhoufi, Maha Jazouli, Aicha majda, Arsalane Zarghili and Rachid Aalouane, “Automatic Recognition of Facial Expressions using Microsoft Kinect with artificial neural network,” International Conference on Engineering & MIS (ICEMIS), Sep. 2016.
[2]Laurindo Britto Neto, Felipe Grijalva, Vanessa Regina Margareth Lima Maike, Luiz Cesar Martini, Dinei Florencio, Maria Cec´ılia Calani Baranauskas, Anderson Rocha and Siome Goldenstein, “A Kinect-Based Wearable Face Recognition System to Aid Visually Impaired Users,” IEEE Transactions on Human-Machine Systems, pp. 1-13, Sep. 2016.
[3]Yunda Liu, Min Dong, Sheng Bi, Dakui Gao, Yuan Jing and Lan Li, “Gesture Recognition Based on Kinect,” The 6th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems, pp.19-22, June 2016.
[4]Kinect v1和Kinect v2的徹底比較, http://www.cnblogs.com/TracePlus.
[5]K. Khoshelham and S. O. Elberink, “Accuracy and Resolution of Kinect Depth Data for Indoor Mapping Applications,” Sensors, vol. 12, no. 2, pp. 1437-1454, 2012.
[6]黃怡菁、黃乙白、謝漢萍，3D立體顯示技術，科學發展，第451冊，46-52頁，2010年。
[7]賴文能、陳韋志，淺談2D至3D視訊轉換技術，影像與識別期刊，第16冊，第2期，61-75頁，2010年。
[8]M. Bertalmío, G. Sapiro, V. Caselles and C. Ballester, “Image Inpainting,” Proceedings of SIGGRAPH 2000, pp. 417-424, July 2000.
[9]A. Crimibisi, P. Pérez and K. Toyama, “Region Filling and Object Removal by Exemplar-based Image Inpainting,” IEEE Transactions on Image Processing, vol. 13, no. 9, pp. 1200-1212, 2004.
[10]P. Goyal Anupam and S. Diwakar, “Fast and Enhanced Algorithm for Exemplar based Image Inpainting,” Pacific-Rim Symposium on Image and Video Technology (PSIVT), pp. 325-330, 2010.
[11]A. Efros and T. Leung, “Texture Synthesis by Non-parametric Sampling,” Proc. Int. Conf. Computer Vision, Greece, pp. 1033-1038, 1999.
[12]Jian Sun, Lu Yuan, Jiaya Jia and Heung-Yeung Shum, “Image Completion with Structure Propagation,” Proceedings of SIGGRAPH 2005, pp. 861-868, July 2005.
[13]M. Solh and G. AlRegib, “Hierarchical Hole-Filling for Depth-Based View Synthesis in FTV and 3D Video,” IEEE Journal of Selected Topics in Signal Processing, vol. 6, no. 5, pp. 495-504, Sept. 2012.
[14]Alexandru Telea, “An Image Inpainting Technique Based on the Fast Marching Method,” Journal Graphics Tools, vol. 9, pp. 25-36, May 2004.
[15]Christoph Fehn, Rene De La Barre and Siegmund Pastoor, “Interactive 3D-TV-Concepts and Key Technologies,” Proceedings of the IEEE, vol. 94, no. 3, pp. 524-538, 2006.
[16]Carlos Vazquez, Wa James Tam and Filippo Speranza, “Stereoscopic Imaging: Filling Disoccluded Areas in Depth Image-Based Rendering,” SPIE Three-Dimensional TV, Video, and Display (ITCOM), vol. 6392, Boston, MA, Oct. 2006.
[17]W. J. Tam, G. Alain, L. Zhang, T. Martin and R. Renaud, “Smoothing Depth Maps for Improved Stereoscopic Image Quality,” SPIE Three-Dimensional TV, Video, and Display III, vol. 5599, pp. 162-172, 2004
[18]C. Fehn, “Depth-Image-Based Rendering (DIBR), Compression and Transmission for a New Approach on 3D-TV,” SPIE Conf. Stereoscopic Displays and Virtual Reality Systems, vol. 5291, pp. 93-104, 2004.
[19]Yuan-Yuan Liu, Die-Cong Shen and Wen-Yu Cai, “Algorithm of View Synthesis Based on DIBR,” Sixth International Conference on Instrumentation and Measurement, Computer, Communication and Control, pp. 1021-1025, 2016
[20]L. Zhang and W. J. Tam, “Stereoscopic Image Generation Based on Depth Images for 3D TV,” IEEE Trans. on Broadcasting, vol. 51, no. 2, pp. 191-199, 2005.
[21]Chih-Hsien Hsia, “Improved Depth Image-Based Rendering Using an Adaptive Compensation Method on an Autostereoscopic 3-D Display for a Kinect Sensor,” IEEE Sensors Journal, vol. 15, no. 2, February 2015.
[22]J. Liu, X. Gong and J. Liu, “Guided Inpainting and Filtering for Kinect Depth Maps,” International Conference on Pattern Recognition (ICPR 2012), pp. 2055-2058, 2012.
[23]D.V.S.X. De Silva, W.A.C. Fernando and H. Kodikara Arachchi, “A New Mode Selection Technique for Coding Depth Maps of 3D Video,” IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 686-689, 2010.
[24]Sang-Beom Lee and Yo-Sung Ho, “Real-time Stereo View Generation Using Kinect Depth Camera,” Asia Pacific Signal Information Processing Association Annual Summit and Conference, 2011.
[25]C. L. Zitnick, S. B. Kang, M. Uyttendaele, S. Winder and R. Szeliski, “High-Quality Video View Interpolation Using a Layered Representation,” ACM Trans. Graph., vol. 23, pp. 600-608, Aug 2004.