請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/54042完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 貝蘇章(Soo-Chang Pei) | |
| dc.contributor.author | Shi-Han Zhou | en |
| dc.contributor.author | 周詩涵 | zh_TW |
| dc.date.accessioned | 2021-06-16T02:37:42Z | - |
| dc.date.available | 2016-07-29 | |
| dc.date.copyright | 2015-07-29 | |
| dc.date.issued | 2015 | |
| dc.date.submitted | 2015-07-24 | |
| dc.identifier.citation | [1] R. Keys, 'Cubic convolution interpolation for digital image processing,” IEEE Trans. on Acoustics, Speech, and Signal Processing 29 (6), pp. 1153–1160, 1981.
[2] Freeman, W. T., Jones, T. R., and Pasztor, “Example-based super-resolution,” IEEE Computer Graphics and Applications 22, pp. 56–65, 2002. [3] C. Fehn., “A 3D-TV approach using depth-image-based rendering (DIBR),” Proceedings of the Visualization, Imaging, and Image Processing, pp. 482–487, 2003 [4] H. Hirschmuller and D. Scharstein. “Evaluation of stereo matching costs on images with radiometric differences,” IEEE TPAMI, 31(9):1582–1599, 2009. [5] D. Scharstein and R. Szeliski, “A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms,” Int’l J. Computer Vision, 2002. [6] T. Kanade.,”Development of a video-rate stereo machine. In Image Understanding Workshop,” pp. 549–557, Monterey, CA, 1994. Morgan Kaufmann Publishers. [7] P. Anandan., “A computational framework and an algorithm for the measurement of visual motion,” IJCV, pp. 283–310, 1989. [8] M. J. Hannah, “Computer Matching of Areas in Stereo Images,” PhD thesis, Stanford University, 1974. [9] L. Matthies, R. Szeliski, and T. Kanade, “Kalman Filter-based Algorithms for Estimating Depth from Image Sequences,” IJCV, pp. 209–236, 1989. [10] E. P. Simoncelli, E. H.Adelson, and D. J. Heeger, “Probability distributions of optic flow,” CVPR, pp. 310–315, 1991. [11] Y. K. Baik, J. H. Jo, and K. M. Lee, “Fast census transform-based stereo algorithm using SSE2,” in Proc. 12th Korea Jpn. Joint Workshop Frontiers Comput. Vis. (FCV), 2006, pp. 305–309. [12] Y. S. Heo, K. M. Lee, and S. U. Lee, 'Robust stereo matching using adaptive normalized cross-correlation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 4, pp. 807-822, April 2011. [13] B. Ham, D. Min, C. Oh, M. Do, and K. Sohn, “Probability-based rendering for view synthesis,” IEEE Trans. Image Process., vol. 23, no. 2, pp. 870–884, Feb. 2014. [14] J. van de Weijer and R. van den Boomgaard, 'Local mode filtering,” IEEE Computer Soc. Conf. Computer Vis. Pattern Recognit., pp. 428 -433, 2001 [15] K. He, J. Sun, and X. Tang. Guided image filtering. In ECCV, 2010. [16] Z. Ma, K. He, Y. Wei, J. Sun, and E. Wu., “Constant Time Weighted Median Filtering for Stereo Matching and Beyond,” In ICCV, 2013. [17] Q. Zhang, J. Jia, “100+ times faster weighted median filter (WMF),” IEEE Conf. Computer Vision and Pattern Recognition, pp. 2830–2837, 2014. [18] C. Lee and Y. S. Ho, 'View Synthesis using Depth Map for 3D Video,' APSIPA ASC 2009, pp. 350-357, 2009. [19] N. Manap and J. Soraghan, “Novel View Synthesis based on Depth Map Layers Representation,” In 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTVCON), pp. 1–4, May 2011. [20] A. Giachetti and N. Asuni, 'Fast Artifact Free Image Interpolation', Proc. Brit. Machine Vis. Conf. (BMVC), pp.123 -132, 2008 [21] Xiangjun Zhang and Xiaolin Wu, 'Image Interpolation by Adaptive 2D Autoregressive Modeling and Soft-Decision Estimation', IEEE Trans. Image Processing, Vol. 17, No. 6, Page(s): 887-896, June 2008. [22] S. Mallat and G. Yu, 'Super-resolution with sparse mixing estimators', IEEE Trans. Image Process., vol. 19, no. 11, pp.2889 -2900, 2010. [23] Weisheng Dong, Lei Zhang, Guangming Shi, and Xiaolin Wu, 'Nonlocal back-projection for adaptive image enlargement', in Proc. ICIP 2009. [24] H. Takeda , S. Farsiu and P. Milanfar, 'Kernel regression for image processing and reconstruction', IEEE Trans. Image Process., vol. 16, no. 2, pp.349 -366 2007 [25] David A. Forsyth and Jean Ponce, “Computer Vision: A Modern Approach,” Prentice Hall, 2003. [26] S. Das and N. Ahuja, “Performance analysis of stereo, vergence, and focus as depth cues for active vision,” IEEE Trans Pattern Analysis & Machine Intelligence, 17:1213–1219, 1995. [27] T. Kanade and M. Okutomi, 'A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, Sept. 1994. [28] Y. Boykov, O. Veksler, and R. Zabih, 'A Variable Window Approach to Early Vision,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 12, pp. 1283-1294, 1998. [29] D. Scharstein and R. Szeliski. High-accuracy stereo depth maps using structured light. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), volume 1, pages 195-202, Madison, WI, June 2003. [30] R. Zabih, J. Woodfill, “Non-parametric local transforms for computing visual correspondence,” ECCV, vol. 801, pp. 151–158, 1994 [31] T. S. Huang , G. J. Yang and G. Y. Tang , 'A fast two-dimensional median filtering algorithm', IEEE Trans., vol. ASSP-27, no. 1, pp.13 -18, 1979 [32] D. Sun, S. Roth, and M. Black, “Secrets of optical flow estimation and their principles,” In CVPR, 2010. [33] C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz, “Fast cost-volume filtering for visual correspondence and beyond,” In CVPR, 2011. [34] C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” In ICCV, 1998. [35] C. Wang, L. Zhao, Z. Qi and J. Xi, 'A Novel Intermediate View Synthesis Method Based on Disparity Estimation,' Proceeding of the first IEEE International Conference on Information Sceince and Engineering (ICISE 09), pp. 1079-1082, 2009. [36] N.A. Manap and J.J. Soraghan, 'Novel View Synthesis based on Depth Map Layers Representation,' in 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), Antalya, Turkey, pp. 1-4, May 2011. [37] X. Li and M. T. Orchard, 'New edge-directed interpolation', IEEE Trans. Image Process., vol. 10, no. 10, pp.1521 -1527, 2001 [38] B.S. Morse and D. Schwartzwald, “Image magnification using level-set reconstruction,” In Proc. IEEE Conf. Comp. Vis. Patt. Rec., vol. 3, pp. 333–340, 2001. [39] M. P. Wand and M. C. Jones, “Kernel Smoothing,” ser. Monographs on Statistics and Applied Probability. New York: Chapman & Hall, 1995. [40] P. Yee and S. Haykin, “Pattern classification as an ill-posed, inverse problem: a reglarization approach,” in Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing, Apr. 1993, vol. 1, pp. 597–600. [41] K. Ratakonda and N. Ahuja, 'POCS based adaptive image magnification', Proc. IEEE Int. Conf. Image Processing, vol. 3, pp.203 -207 1998 [42] R. Fattal, “Upsampling via imposed edges statistics,” ACM Transactions on Graphics (Proceedings of SIGGRAPH 2007), 26(3):95:1-95:8, 2007. 449, 454, 455 [43] John Canny, “A computational approach to edge detection,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, PAMI-8(6):679–698, Nov. 1986. [44] H. Hirschmüller and D. Scharstein, “Evaluation of cost functions for stereo matching,” In IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), Minneapolis, MN, June 2007. [45] D. Scharstein, H. Hirschmüller, Y. Kitajima, G. Krathwohl, N. Nesic, X. Wang, and P. Westling, “High-resolution stereo datasets with subpixel-accurate ground trut,” GCPR 2014, Münster, Germany, September 2014. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/54042 | - |
| dc.description.abstract | 本論文研究兩種影像處理的技術，包含深度圖(depth image)計算以及影像放大(image upsampling)技術，隨著科技日益成長，立體視覺技術廣泛應用於多媒 體及電視影像中，利用立體視覺演算法得到以目標深度為主的資訊，主要藉由兩張影像的特徵點進行比對，找出每個像素點之間的位置差，稱為像差(disparity)，最後以立體視覺成像原理計算出目標深度圖，進而利用深度圖資訊進行新視點圖像的合成(view synthesis)。
一般影像及深度影像放大廣泛應用於電腦視覺處理及3D影像處理中，我們提出一個簡單且有效率的影像放大方法，其中可自動提升影像的解析度並保留影像的重要資訊，透過還原成像程序將影像重組至最接近實物的狀況，快速提升影像至高清規格，有別於傳統的影像放大技術，如最鄰近內插法(nearest interpolation)、雙線性內插法(bilinear interpolation)、雙立方內插法(bicubic interpolation)等，本論文提出適應性區域加權核心(Adaptive Local Weighted Kernel)的影像放大技術可以應用在深度圖以及一般影像上，利用適應性加權核心與低解析度原圖相對應的區域做卷積(convolution)，內插出位在各個原始像素之間的新像素值，進而在快速求出高解析度影像，並針對不同影像來源產生其相對應的加權核心，可以有效提高各個放大影像的訊噪比。另一方面，提出的演算法架構未來可以應用在現今電視2K (High Definition)轉4K (Quad Full High Definition)的影像處理技術中，目的在於將影像以更高效的方式內插出高解析的放大影像。 | zh_TW |
| dc.description.abstract | In this thesis, we study two topics about image processing, including depth image extraction and image upsampling. With the growing of technology, stereoscopic vision widely apply to image processing on multimedia and television. We find depth information of images by using stereo correspondence algorithms. The main idea of algorithms is matching feature points of two images, and then finding the position difference between every pixel, which is called disparity. Finally, the depth value can be obtained by the principle of stereo matching algorithm, and then we use these depth map information to conduct the application of view synthesis.
Images and depth images upsampling are generally used in computer vision and 3D image processing. We propose a simple but effective upsampling method for automatically enhancing the image resolution, while preserving the essential structural information. The main idea is reconstructing images through the procedure of image recovering, that upsample low resolution to high resolution images quickly and get close to ground truth images. Different from the traditional upsampling technique, such as nearest interpolation, bicubic interpolation and etc. We proposed a method, called Adaptive Local Weighted Kernel, which can both apply to depth images and generic images. In undetermined upsampling images, unknown pixels between every original pixel will be interpolated by the convolution of low resolution image and Adaptive Local Weighted Kernel in the corresponding window size, thus this method can upsample images to high resolution rapidly. According to different image sources, the proposed algorithm will generate adaptive weighting to enhance edges, details and image quality of upsampling images respectively. On the other hand, the proposed algorithm can be applied to the new technique in image processing of television in the future, which can change image resolution from 2K(High Definition) to 4K (Quad Full High Definition) in high speed. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T02:37:42Z (GMT). No. of bitstreams: 1 ntu-104-R02942033-1.pdf: 6274867 bytes, checksum: f98898c979339a11c38c1c3c994f71e4 (MD5) Previous issue date: 2015 | en |
| dc.description.tableofcontents | 口試委員會審定書........................................................................................................ #
誌謝 ............................................................................................................................................ i 中文摘要 .................................................................................................................................. iii ABATRACT ............................................................................................................................. v CONTENTS ............................................................................................................................ vii LIST OF FIGURES .................................................................................................................. ix LIST OF TABLES ................................................................................................................. xiv Chapter 1 Introduction ....................................................................................................... 1 Chapter 2 Depth Image ..................................................................................................... 10 2.1 Stereo Vision and Camera Calibration ................................................................... 13 2.2 Stereo Matching Algorithm ................................................................................... 18 2.4.1 Sum of Absolute Differences (SAD) ................................................................. 23 2.4.2 Sum of Squared Differences (SSD) ................................................................... 25 2.4.3 Sum of Hamming Distances (SHD) .................................................................. 27 2.4.4 Normalized Cross Correlation (NCC) ............................................................... 28 2.4.5 Steady-State Matching Probability (SSMP) ...................................................... 29 2.5 Disparity Refinement ............................................................................................. 32 2.5.1 Local Mode Filter .............................................................................................. 33 2.5.2 Weighted Median Filter ..................................................................................... 35 2.5.3 100+ Weighted Median Filter ............................................................................ 36 2.6 Experiment Result of Depth Estimation ................................................................ 38 2.7 View Synthesis ....................................................................................................... 49 2.7.1 Disparity Depth Layer Separation ..................................................................... 51 2.7.2 Intermediate View Synthesis ............................................................................. 53 Chapter 3 Overview of Previous Works on Image Upsampling .................................... 58 viii 3.1 Introduction of Image Upsampling ........................................................................ 58 3.2 Nearest Neighbor Interpolation .............................................................................. 60 3.3 Bilinear Interpolation ............................................................................................. 62 3.4 Bicubic Convolution Interpolation ......................................................................... 63 3.5 Iterative Curvature Based Interpolation (ICBI) ..................................................... 66 3.6 Kernel Regression .................................................................................................. 69 Chapter 4 Proposed Method for Image and Depth Image Upsampling ....................... 71 4.1 Introduction ............................................................................................................ 71 4.2 Adapted Local Weighted Kernel ............................................................................ 73 4.3 Experiment of Image Upsampling ......................................................................... 77 4.4 View Synthesis in Higher resolution...................................................................... 92 Chapter 5 Conclusion and Future Work ......................................................................... 97 5.1 Conclusion ............................................................................................................. 97 5.2 Future Work ........................................................................................................... 97 REFERENCE ........................................................................................................................ 99 | |
| dc.language.iso | en | |
| dc.subject | 新視點圖像合成 | zh_TW |
| dc.subject | 像差 | zh_TW |
| dc.subject | 深度圖 | zh_TW |
| dc.subject | 雙三次內插 | zh_TW |
| dc.subject | 新視點圖像合成 | zh_TW |
| dc.subject | 適應性區域加權核心 | zh_TW |
| dc.subject | 影像放大 | zh_TW |
| dc.subject | 像差 | zh_TW |
| dc.subject | 深度圖 | zh_TW |
| dc.subject | 適應性區域加權核心 | zh_TW |
| dc.subject | 最鄰近內插法 | zh_TW |
| dc.subject | 雙三次內插 | zh_TW |
| dc.subject | 最鄰近內插法 | zh_TW |
| dc.subject | 影像放大 | zh_TW |
| dc.subject | image upsampling | en |
| dc.subject | depth image | en |
| dc.subject | disparity | en |
| dc.subject | view synthesis | en |
| dc.subject | nearest interpolation | en |
| dc.subject | bicubic interpolation | en |
| dc.subject | adaptive local weighted kernel | en |
| dc.subject | depth image | en |
| dc.subject | disparity | en |
| dc.subject | view synthesis | en |
| dc.subject | image upsampling | en |
| dc.subject | nearest interpolation | en |
| dc.subject | bicubic interpolation | en |
| dc.subject | adaptive local weighted kernel | en |
| dc.title | 利用適應性區域加權核心放大影像及深度影像 | zh_TW |
| dc.title | Image and Depth Image Upsampling Using Adaptive Local Weighted Kernel | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 103-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 黃文良,林康平,祁忠勇,鍾國亮 | |
| dc.subject.keyword | 深度圖,像差,新視點圖像合成,影像放大,最鄰近內插法,雙三次內插,適應性區域加權核心, | zh_TW |
| dc.subject.keyword | depth image,disparity,view synthesis,image upsampling,nearest interpolation,bicubic interpolation,adaptive local weighted kernel, | en |
| dc.relation.page | 103 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2015-07-24 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-104-1.pdf 未授權公開取用 | 6.13 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。