(3.236.122.9) 您好!臺灣時間:2021/05/14 06:53
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:::

我願授權國圖
: 
twitterline
研究生:白孟哲
研究生(外文):Meng-ChengBai
論文名稱:2D轉3D自動化深度預測之研究
論文名稱(外文):The Study of Automatic 2D-to-3D Depth Estimation
指導教授:郭淑美郭淑美引用關係
指導教授(外文):Shu-Mei Guo
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資訊工程學系
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:2016
畢業學年度:104
語文別:英文
論文頁數:60
中文關鍵詞:2D轉3D深度預測基於資料庫學習消失線偵測
外文關鍵詞:2D-to-3Ddepth estimationlearning basedvanishing line detection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:154
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
我們提出了一個基於資料庫學習和幾何學之自動化2D轉3D深度預測的方法;由於使用資料庫學習的方法,因此對於待轉換的影像或影片沒有任何場景限制,同時藉由幾何學的消失點亦能優化預測深度結果。為了加速整體演算法的計算速度,我們會預先計算資料庫中所有2D影像的影像特徵,接下來在找出影像特徵最相似的圖片步驟時,便只需計算待轉換影像的特徵並比較其差異,如此能大量減少演算法執行時間。另外,本論文也會介紹到如何將前一幀之深度圖繁殖到場景相似的影像中。經實驗測試,所提出演算法的預測深度圖,除了在視覺上更接近真實深度外,在PSNR和視覺資訊忠誠 (VIF)量化測試上也可以比其他方法得到更佳的成果。
In the current work, we have proposed an automatic 2D-to-3D depth estimation method. It is primarily based on learning and geometry. Because it is a learning-based algorithm, it has no restriction on the scene of the input image or video. The new method can also refine the depth estimation result by vanishing point in geometry. In order to accelerate the computing speed of the overall algorithm, we extract the features of 2D images in the database in advance. Next, to find the most similar images within the database by image features, the only necessary thing to do is to compute the feature of the query image and compare the difference between the query image and training images. Such an approach can reduce computing time. Furthermore, the paper also introduces the method of propagating depth value to video with similar scenes. The experimental results show that the depth map of our algorithm is not only closely similar to ground truth, but also the PSNR and VIF (visual information fidelity) show better performance than other reported algorithms.
Table of Contents
摘要 I
Abstract II
誌謝 III
Table of Contents IV
List of Tables VI
List of Figures VII
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 System Architecture 3
1.3 Thesis Architecture 4
Chapter 2 Background 6
2.1 GIST and HOG 6
2.2 Vanishing line and vanishing point 12
2.3 Key frame detection 15
2.4 PSNR, VIF and SSIM 16
Chapter 3 2D-to-3D depth map estimation 25
3.1 Key frame depth estimation algorithm 25
3.1.1 kNN (k-nearest neighbor algorithm) 30
3.1.2 Depth fusion 30
3.1.3 Object segmentation 34
3.1.4 Vanishing line detection 35
3.1.5 Depth refinement 39
3.2 Non-key frame depth estimation algorithm 41
3.2.1 Motion estimation 43
3.2.2 Motion compensated interpolation 43
Chapter 4 Experimental Results 45
4.1 Best k for kNN Search 45
4.2 Depth map estimation 46
Chapter 5 Conclusions 56
References 58


[1]X. Cao, Z. Li, and Q. Dai, “Semi-Automatic 2D-to-3D Conversion Using Disparity Propagation, IEEE Trans. Broadcast., vol. 57, no. 2, pp. 491-499, 2011.
[2]M. Liao, J. Gao, R. Yang and M. Gong, “Video Stereolization: Combining Motion Analysis with User Interaction, IEEE Trans. Visualiza. and Comput. Graph., vol. 18, no. 7, pp. 1079-1088, Jul., 2012.
[3]X. Huang, L. Wang, J. Huang, D. Li, M. Zhang, “A Depth Extraction Method Based On Motion and Geometry for 2D to 3D Conversion, 3rd Int. Symp. Intell. Inf. Technol. Appl., pp. 294-298, 2009.
[4]Y.-K. Lai, Y.-F. Lai, and Y. C. Chen, “An Effective Hybrid Depth-Generation Algorithm for 2D-to-3D Conversion in 3D Displays, J. Display Technol., vol. 9, no. 3, pp. 154-161, Mar. 2013.
[5]C.-C. Cheng, C.-T. Li, and L.-G. Chen, “A Novel 2D-to-3D Conversion System Using Edge Information, IEEE Trans. On Consumer Electronics, vol. 56, no. 3, Aug. 2010.
[6]C.-T. Li, Y. C. Lai, C. Wu, S. F. Tsai, T. C. Chen, S. Y. Chien, et al., “Brain-Inspired Framework for Fusion of Multiple Depth Cues, IEEE Trans. Circuits Syst. Video Technol., vol. 23, no. 7, pp. 1137-1149, Oct 2013.
[7]Y. C. Fan, Y. C. Chen, and S. Y. Chou, “Vivid-DIBR Based 2D–3D Image Conversion System for 3D Display, J. Display Technol., vol. 10, no. 10, pp. 859-870, Oct. 2014.
[8]Y. Feng, J. Ren, and J. Jiang, “Object-Based 2D-to-3D Video Conversion for Effective Stereoscopic Content Generation in 3D-TV Applications, IEEE Trans. Broadcast., vol. 57, no. 2, pp. 500-509, Jun. 2011.
[9]A. Saxena, S. H. Chung, and A. Y. Ng, “Learning depth from single monocular images, in Advances in Neural Info. Proc. Syst.,18, 2005.
[10]J. Konrad, G. Brown, M. Wang, P. Ishwar, C. Wu, and D. Mukherjee, “Automatic 2d-to-3d image conversion using 3d examples from the internet, in SPIE 8288, Stereoscopic Displays and Applications, vol.82880F, Jan. 2012.
[11]K. Karsch, C. Liu, and S. B. Kang, “DepthTransfer: Depth Extraction from Video Using Non-Parametric Sampling, IEEE Trans. on Pattern Anal. Mach. Intell., vol. 36, no. 11, pp. 2144-2158, Nov. 2014.
[12]Janusz Konrad, Meng Wang, Prakash Ishwar, Chen Wu, and Debargha Mukherjee, “Learning-Based, Automatic 2D-to-3D Image and Video Conversion, IEEE Trans. Image Process., vol. 22, no. 9, pp. 3485-3496, Sep. 2013.
[13]L. Wang and C. Jung, “Example-Based Video Stereolization With Foreground Segmentation and Depth Propagation, IEEE Transactions on Multimedia, vol. 16, no. 7, pp. 88-98, Nov. 2014.
[14]A. Oliva and A. Torralba, “Modeling the shape of the scene: A holistic representation of the spatial envelope, Int. J. Comput. Vis., vol. 42, no. 3, pp. 145–175, 2001.
[15]N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection, in Proc. IEEE CVPR, pp. 886-893, 2005.
[16]C. Christoudias, B. Georgescu, P. Meer, “Synergism in low-level vision, IEEE Conference on Pattern Recognition, 2002.
[17]N. Silberman, D. Hoiem, P. Kohli, and R. Fergus, “Indoor segmentation and support inference from RGBD images, in Proc. Eur. Conf. Comput. Vis., pp. 746-760, 2012.
[18]H. R. Sheikh, and A. C. Bovik, “Image Information and Visual Quality, IEEE Trans. Image Processing, vol. 15, no. 2, pp. 430-444, Feb. 2006.
[19]Liu C. Freeman, W. Adelson E., Weiss Y., “Human-assisted motion annotation, In Proceedings of the IEEE conference on computer vision and pattern recognition, 2008.
[20]S. Baker, D. Scharstein, J. Lewis, S. Roth, M. J. Black, and R. Szeliski. A database and evaluation methodology for optical flow. In Proc. IEEE International Conference on Computer Vision (ICCV), 2007.

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
無相關期刊
 
無相關點閱論文
 
系統版面圖檔 系統版面圖檔