跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.64) 您好!臺灣時間:2021/08/04 18:56
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:吳思憲
研究生(外文):Sih-SianWu
論文名稱:雙視角轉多視角之立體視訊合成與GPU 協同設計
論文名稱(外文):Two-view to Multiview Video Synthesis and Its GPU Co-Design
指導教授:劉濱達楊家輝楊家輝引用關係
指導教授(外文):Bin-Da LiuBin-Da Liu
學位類別:碩士
校院名稱:國立成功大學
系所名稱:電機工程學系碩博士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:英文
論文頁數:81
中文關鍵詞:雙視角轉多視角立體視訊合成立體匹配全系統模擬視角合成
外文關鍵詞:Image-Based Rendering (IBR)Cross-based Stereo MatchingView SynthesisDIBR
相關次數:
  • 被引用被引用:0
  • 點閱點閱:157
  • 評分評分:
  • 下載下載:4
  • 收藏至我的研究室書目清單書目收藏:0
本論文提出雙視角轉多視角之立體視訊合成系統,系統中包含立體匹配、深度圖前處理以及多維視訊合成技術,並以圖形處理器實現此系統。立體匹配演算法的部分採取改良過的十字區塊立體匹配法,並採取以區塊為基礎之設計方式,來改善圖形處理器資源有限的問題。深度圖前處理的部分,先採取左右深度圖檢測之方式,找出深度值不可靠區域,然後根據其不匹配區塊與遮蔽區塊,個別執行不同的處理方式,至於深度值不正確的問題,則以反覆投票法以及適切取代法來解決之。多維視訊合成方式,是使用原有的兩個不同視角圖與經過前處理的深度圖作為輸入資料以產生額外的視角圖。本論文所設計之雙視角轉多視角視訊的系統,僅需雙視角的影像輸入,即可產生多視角的視訊結果,並在結果中顯示七個視角的合成圖。本論文提出之技術,以QEMU做系統模擬並於圖形處理器執行以CUDA撰寫之程式,經由模擬的方式分析所提出之技術移植至嵌入式系統的情況。實驗結果顯示本系統可以即時處理解析度為450 × 375 之視訊並產生額外七個視角之視訊。
An Image-Based Rendering (IBR) system is proposed in this thesis. The designed system is composed of three major parts Stereo Matching, Depth Map Refinement, and View Synthesis. Cross-base Stereo Matching is applied in the proposed system which is modified with Block-based character because of the finite graphics hardware resources. Left-Right check consistency scheme is applied to identify the depth map is a reliable or not. Iterative Voting and Interpolation are involved in the refinement of depth map to solve mismatches and occlusions problems. View Synthesis parts treats two different views and one depth map which is produced by this system as input data. In the proposed method, only two views are required for synthesis multi-view, take seven views as example. QEMU is adapted to simulate the embedded system of porting target application. The result of the system prove its ability to handle 450 x 375 frames in real-time constrain.
Abstract(Chinese) i
Abstract(English) iii
Acknowledgement v
Table of Contents vii
List of Figures ix
List of Tables xiii
Chapter 1 Introduction 1
1.1 Motivation 2
1.2 Organization for the Thesis 5
Chapter 2 Related Work 7
2.1 Stereo Matching 8
2.2 View Synthesis 12
2.3 Refinement 18
2.4 IBR system 20
2.5 CUDA 21
2.6 QEMU 23
2.7 3D content 25
Chapter 3 Proposed Method 27
3.1 Stereo Matching Part 30
3.1.1 Binary tree cost aggregation 41
3.1.2 Block-based design 42
3.2 Refinement Part 47
3.2.1 Left-right consistency check 47
3.2.2 Iterative Cross-based region voting 48
3.2.3 Interpolation 49
3.3 View Synthesis Part 51
Chapter 4 Experimental Results and Comparisons 59
4.1 Experimental Environment Settings 59
4.2 Experiment Result 63
Chapter 5 Conclusions and Future Work 71
5.1 Conclusion 72
5.2 Future Work 72
References 75

[1]CUDA ZONE. [Online]. Available: http://developer.nvidia.com/category/zone/cuda-zone.
[2]J. L. Hennessy and D. A. Patterson, Computer Architecture: A Quantitative Approach. San Francisco, CA: Elsevier Science, 2011, pp. 2-5.
[3]C. Fehn, A 3D-TV system based on video plus depth information, in Proc. 37th Asilomar Conf. on Signals, Syst. and Comput., Pacific Grove, Calif, USA, Nov. 2003, vol. 2, pp. 1529-1533.
[4]D. Scharstein and R. Szeliski, A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, Int. J. Comput. Vision, vol. 47, pp. 7-42, 2002.
[5]A. Ogale and Y. Aloimonos, Shape and the stereo correspondence problem, Int. J. Comput. Vision, vol. 65, pp. 147-162, 2005.
[6]S. Jian, Y. Li, S. B. Kang, and H. Y. Shum, Symmetric stereo matching for occlusion handling, in Proc. IEEE Comput.Soc. Conf. Comput. Vision and Pattern Recognition, San Diego, CA, USA, June 2005, vol. 2 pp. 399-406
[7]K. J. Yoon and I. S. Kweon, Adaptive support-weight approach for correspondence search, IEEE Trans.Pattern Annl. Mach. Intell., vol. 28, pp. 650-656, 2006.
[8]A. Fusiello, V. Roberto, and E. Trucco, Efficient stereo with multiple windowing, in Proc. IEEE Comput.Soc. Conf. Comput. Vision and Pattern Recognition, San Juan, Puerto Rico, June 1997, pp. 858-863.
[9]S. B. Kang, R. Szeliski, and J. Chai, Handling occlusions in dense multi-view stereo, in Proc. IEEE Comput.Soc. Conf. Comput. Vision and Pattern Recognition, Kauai, HI, USA, June 2001, vol.1., pp. I-103-I-110
[10]O. Veksler, Stereo matching by compact windows via minimum ratio cycle, IEEE Trans.Pattern Annl. Mach. Intell., vol. 24, pp. 1654-1660, 2002.
[11]K. Zhang, J. Lu, and G. Lafruit, Cross-based local stereo matching using orthogonal integral images, IEEE Trans. Cir. and Sys. Video Technol., vol. 19, pp. 1073-1079, 2009.
[12]N. W. Tham, Low Complexity Cross-Based Local Stereo-Matching for Fast Depth Estimation, Master thesis, National Chung Kung University, Tainan, Taiwan, July 2011.
[13]C. Fehn, Depth-image-based rendering (DIBR) , compression, and transmission for a new approach on 3D-TV, Proc. SPIE Conf. Stereoscopic Displays and Virtual Reality Systems XI, vol. 5291, pp. 93 -104, 2004.
[14]C. Vazquez, W. J. Tam, and F. Speranza, Stereoscopic imaging: filling disoccluded areas in depth image-based rendering, Proc. SPIE Conf. 3D TV, Video and Display V , vol.6392, pp. 63920D 2006.
[15]W. Y. Chen, Y. L. Chang, S. F. Lin, L. F. Ding, and C. L. G. Chen, Efficient depth image based rendering with edge dependent depth filter and interpolation, in Proc. IEEE int. Conf. Multimedia and Expo, Amsterdam, The Netherlands, 2005, pp. 1314-1317.
[16]Z. Liang, W. J. Tam, and D. Wang, Stereoscopic image generation based on depth images, in Proc. Int. Conf. Image Proces., Singapore, Oct 24-27 2004, pp. 2993-2996 Vol. 5.
[17]C. Ballester, M. Bertalmio, V. Caselles, L. Garrido, A. Marques, and F. Ranchin, An Inpainting- Based Deinterlacing Method, IEEE Trans. Image Process., vol. 16, pp. 2476-2491, 2007.
[18]G. D. Finlayson, S. D. Hordley, L. Cheng, and M. S. Drew, On the removal of shadows from images, IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, pp. 59-68, 2006.
[19]Z. Liang and W. J. Tam, Stereoscopic image generation based on depth images for 3D TV, IEEE Trans. Broadcast., vol. 51, pp. 191-199, 2005.
[20]M. Solh and G. AlRegib, Hierarchical hole-filling (HHF) : depth image based rendering without depth map filtering for 3D-TV, in Proc. IEEE Int. Workshop in Multimedia Signal Process, Saint-Malo, France, Oct. 4-6 2010, pp. 87-92.
[21]I. Daribo and H. Saito, A novel inpainting-based layered depth video for 3DTV, IEEE Trans. Broadcast. vol. 57, pp. 533-541, 2011.
[22]A. Boev, D. Hollosi, A. Gotchev, and K. Egiazarian, Classification and simulation of stereoscopic artifacts in mobile 3DTV content, Proc. SPIE Stereoscopic Displays and Applications XX, vol. 7237, No. 1, pp. 72371F1-12, 2009.
[23]Y. Ruigang, G. Welch, and G. Bishop, Real-time consensus-based scene reconstruction using commodity graphics hardware, in Proc. 10th Pacific Conf Comput. Graph. and Appl., Beiging, China, Oct. 9-11 2002, pp. 225-234
[24]C. L. Zitnick and S. B. Kang, Stereo for image-based rendering using image over-segmentation, Int. J. Comput. Vision, vol. 75, pp. 49-65, 2007.
[25]G. Egnal and R. P. Wildes, Detecting binocular half-occlusions: empirical comparisons of five approaches, IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, pp. 1127-1133, 2002.
[26]H. C. Shih and H. F. Hsiao, A depth refinement algorithm for multi-view video synthesis, in Proc. IEEE Int. Conf. Acoustics Speech and Signal Processing, Dallas, Texas, USA, March 14-19 2010, pp. 742-745.
[27]O. Stankiewicz, M. Domanski, and K. Wegner, Stereoscopic depth refinement by mid-level hypothesis, in Porc. IEEE Int. Conf. Multimedia and Expo, Copenhagen, Denmark, July 4-11 2010, pp. 950-955.
[28]J. Wu, Y. Zhou, H. Yu, and Z. Zhang, Improved 3D depth image estimation algorithm for visual camera, in Proc. 2nd Int. Congress Image and Signal Processing., Tianjin, China, Oct. 2009, pp. 1-4.
[29]A. Torralba and A. Oliva, Depth estimation from image structure, IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, pp. 1226-1238, 2002.
[30]C. Zhang and T. Chen, A survey on image-based rendering—representation, sampling and compression, IEEE Trans. Circuits Syst. Video Technol., vol. 13, pp. 1020-1037, 2003.
[31]H. Y. Shum, S. C. Chan, and S. B. Kang, Image-Based Rendering. Hanover, MA. USA, Springer, 2007.
[32]S. C. Chan, S. H. Y. Shum, and K. T. Ng, Image-based rendering and synthesis, IEEE Signal Process. Mag., vol. 24, pp. 22-33, 2007.
[33]Z. Tauber, Z. N. Li, and M. S. Drew, Review and preview: disocclusion by inpainting for image-based rendering, IEEE Trans. Syst., Man, Cybern., C Appl. Rev., vol. 37, pp. 527-540, 2007.
[34]J. Lu, S. Rogmans, G. Lafruit, and F. Catthoor, Stream-centric stereo matching and view synthesis: a high-speed approach on GPUs, IEEE Trans Circuits Syst. Video Technol., vol. 19, pp. 1598-1611, 2009.
[35]S. F. Tsai, C. C. Cheng, C. T. Li, and L. G. Chen, A real-time 1080p 2D-to-3D video conversion system, IEEE Trans. Consum. Electron., vol. 57, pp. 915-922, 2011.
[36]M.D. Mccool, Signal processing and general-purpose computing and GPUs [Exploratory DSP],, IEEE Signal Process. Mag., vol. 24, pp. 109-114, 2007.
[37]G. E. Moore, Trends in silicon device technology, in Proc. Int. Electron Devices Meeting, 1968, pp. 12.
[38]R. Chandra, “Parallel Programming in OpenMP, San Francisco, CA: Morgan Kaufmann, 2001, pp. 41-66.
[39]QEMU Home Page. [Online].Available: www.qemu.org/
[40]Wind River Simics. [Online].Available: http://www.windriver.com/products/simics/
[41]SimOS. [Online].Available: http://simos.stanford.edu
[42]Open Virtual Platforms (OVP). [Online].Available: http://www.OVPworld.org
[43]T. C. Yeh and M. C. Chiang, On the interfacing between QEMU and SystemC for virtual platform construction: Using DMA as a case, J. Syst. Archit, vol. 58, pp. 99-111, 2012.
[44]S. T. Shen, S. Y. Lee, and C. H. Chen, Full system simulation with QEMU: An approach to multi-view 3D GPU design, in Proc. IEEE Int. Symp. Circuits and Syst. 2010, Paris, France, May 30- June 2 2010, pp. 3877-3880.
[45]H. Hirschmuller, Stereo processing by semiglobal matching and mutual information, IEEE Trans. Pattern Anal. Mach. Intell., vol. 30, pp. 328-341, 2008.
[46]Y. Qingxiong, W. Liang, Y. Ruigang, H. Stewenius, and D. Nister, Stereo matching with color-weighted correlation, hierarchical belief propagation, and occlusion handling, IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, pp. 492-504, 2009.
[47]M. Xing, S. Xun, Z. Mingcai, J. Shaohui, W. Haitao, and Z. Xiaopeng, On building an accurate stereo matching system on graphics hardware, in Proc. IEEE Int. Conf. Comput. Vision Workshops, Barcelona, Spain, Nov. 6-13 2011, pp. 467-474.
[48]N. Kanopoulos, N. Vasanthavada, and R. L. Baker, Design of an image edge detection filter using the Sobel operator, IEEE J. Solid-State Circuits, vol. 23, pp. 358-367, 1988.
[49]N. Kazakova, M. Margala, and N. G. Durdle, Sobel edge detection processor for a real-time volume rendering system, in Proc. IEEE Int. Symp. Circuits and Syst. .Vancouver, Canada ,May 23-26 2004, pp. II-913-16 Vol.2.
[50]Oracle. Oracle VM VirtualBox. [Online].Available: https://www.virtualbox.org/
[51]VMware. [Online].Available: http://www.vmware.com/
[52]Zale Schoenborn, PCI-SIG: Board Design Guidelines for PCI Express Architecture, Intel Corp., 2004.
[53]Middlebury. [Online].Available: http://www.middlebury.edu/

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top